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. 60258
    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
     django
    -0.07
    season
    -0.07
    -selling
    -0.07
    _SelectedIndexChanged
    -0.07
    害
    -0.06
     volunteered
    -0.06
    PreparedStatement
    -0.06
    ,default
    -0.06
    מתר
    -0.06
     sailed
    -0.06
    POSITIVE LOGITS
    叠加
    0.08
    閱
    0.08
    _adapter
    0.07
     đô
    0.07
    cdn
    0.07
     dục
    0.07
    -peer
    0.06
    Drag
    0.06
     compartment
    0.06
    空间
    0.06
    Activations Density 0.601%

    No Known Activations