© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 62662
    Prev
    Next
    INDEX
    Explanations

    scripted creative writing/roleplay responses—especially anthropomorphic, fan‑fiction–style dialogue with speaker labels and conversational lines.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    יכות
    -0.07
    misc
    -0.07
    avenport
    -0.07
    atura
    -0.07
    ありません
    -0.06
    返还
    -0.06
    פורסם
    -0.06
    *T
    -0.06
     tentative
    -0.06
    paredStatement
    -0.06
    POSITIVE LOGITS
     NODE
    0.07
     YEARS
    0.07
    监理
    0.07
     decryption
    0.07
     Parent
    0.07
    estructor
    0.07
    (Game
    0.06
    调节
    0.06
     callback
    0.06
    Something
    0.06
    Activations Density 0.073%

    No Known Activations