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. 15-RESID-POST-AA
    6. 57334
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     komple
    -0.07
     vigorously
    -0.07
    "With
    -0.07
    .getMax
    -0.07
     الكوي
    -0.07
    ◓
    -0.07
    Hôtel
    -0.07
     extremism
    -0.07
    ♞
    -0.07
    엇
    -0.07
    POSITIVE LOGITS
    .SQL
    0.06
     bụng
    0.06
    쫘
    0.06
     Bell
    0.06
     exports
    0.06
    死亡
    0.06
     questão
    0.06
    龄
    0.06
     Regression
    0.06
    盡
    0.06
    Activations Density 0.011%

    No Known Activations