© 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. 77434
    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
     network
    -0.07
    TableModel
    -0.07
    全力以赴
    -0.06
    졪
    -0.06
    .executeQuery
    -0.06
    ﭰ
    -0.06
    ℃
    -0.06
    .CLASS
    -0.06
    Ť
    -0.06
     yog
    -0.06
    POSITIVE LOGITS
     loudly
    0.08
     однако
    0.07
    dated
    0.07
     pero
    0.07
    ────────
    0.07
    豐富
    0.07
    prt
    0.07
    序幕
    0.07
    (info
    0.07
    upert
    0.07
    Activations Density 0.021%

    No Known Activations