© 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. 84863
    Prev
    Next
    INDEX
    Explanations

    movement

    np_max-act · gemini-2.0-flash
    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
    _req
    -0.07
     specs
    -0.07
    spec
    -0.07
    该怎么办
    -0.07
     sectional
    -0.07
     unchecked
    -0.07
    usr
    -0.07
     panorama
    -0.07
     TODO
    -0.07
     technology
    -0.07
    POSITIVE LOGITS
    鬷
    0.08
    뼛
    0.07
    "]."
    0.07
    ⵟ
    0.07
    𝗞
    0.07
    פעול
    0.07
    )}>↵
    0.06
    .timing
    0.06
     mundane
    0.06
    posites
    0.06
    Activations Density 0.014%

    No Known Activations