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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 89812
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    numeric tokens—especially the digit “2” in years, version numbers, and numeric codes within license or header text.

    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
    曹操
    -0.08
    Such
    -0.07
     очер
    -0.07
    孔子
    -0.07
    ResultsController
    -0.06
     Joan
    -0.06
     Qin
    -0.06
    旌
    -0.06
    inkel
    -0.06
     TELE
    -0.06
    POSITIVE LOGITS
     Mathematical
    0.08
    百货
    0.07
     payments
    0.07
    備
    0.07
    .
    0.07
     Turkish
    0.07
     Nicar
    0.07
    애
    0.06
    跚
    0.06
    ,
    0.06
    Activations Density 0.365%

    No Known Activations