© 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. 11-RESID-POST-AA
    11. 85393
    Prev
    Next
    INDEX
    Explanations

    target

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    在一旁
    -0.07
    天堂
    -0.07
    相连
    -0.07
     conv
    -0.07
     collects
    -0.07
    =".$_
    -0.06
    安心
    -0.06
    /cat
    -0.06
    _bp
    -0.06
     Dome
    -0.06
    POSITIVE LOGITS
    (queue
    0.07
    (binary
    0.07
    rö
    0.07
    _direction
    0.07
    .onerror
    0.07
    ղ
    0.07
    ナイ
    0.07
    тал
    0.07
     Vad
    0.07
    (iterator
    0.07
    Activations Density 0.001%

    No Known Activations