Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 36547
    Prev
    Next
    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ESPN
    -0.08
    acd
    -0.08
     giấ
    -0.07
    QT
    -0.07
    argo
    -0.07
     Además
    -0.07
    arte
    -0.07
    锇
    -0.07
     FG
    -0.07
    patient
    -0.07
    POSITIVE LOGITS
    \Services
    0.06
     roundup
    0.06
    帮
    0.06
    規
    0.06
     reconnaissance
    0.06
    交叉
    0.06
    可能出现
    0.06
    旅程
    0.06
     collected
    0.06
     crashing
    0.06
    Activations Density 0.013%

    No Known Activations