© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 76674
    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
     mm
    -0.08
     quoi
    -0.07
    .power
    -0.07
     FY
    -0.07
    それに
    -0.07
    扭转
    -0.07
     bree
    -0.07
     setName
    -0.07
     пред
    -0.07
     tv
    -0.07
    POSITIVE LOGITS
    seller
    0.07
    serialized
    0.07
     sellers
    0.07
     huyết
    0.07
     FileAccess
    0.07
    入股
    0.07
    ocked
    0.07
    Array
    0.07
     incarceration
    0.07
    텁
    0.07
    Activations Density 0.003%

    No Known Activations