© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 2245
    Prev
    Next
    INDEX
    Explanations

    dynamically

    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
    운동
    -0.09
    _NEAR
    -0.07
    ')")↵
    -0.07
    egade
    -0.07
    sports
    -0.07
    _DET
    -0.07
    (LL
    -0.07
     hopping
    -0.07
    Avg
    -0.06
     Skype
    -0.06
    POSITIVE LOGITS
     templateUrl
    0.08
     فقال
    0.07
    湿
    0.07
     UM
    0.07
    readcrumb
    0.07
     //$
    0.07
     חמ
    0.06
    /pub
    0.06
     fs
    0.06
     born
    0.06
    Activations Density 0.014%

    No Known Activations