© 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. 115499
    Prev
    Next
    INDEX
    Explanations

    ="

    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
     apk
    -0.08
    _operand
    -0.07
    你还
    -0.06
    .ReadAll
    -0.06
    자는
    -0.06
    ’h
    -0.06
    iscing
    -0.06
    耵
    -0.06
    _salt
    -0.06
    /*****************************************************************************↵
    -0.06
    POSITIVE LOGITS
    致力于
    0.08
    阀门
    0.08
     أجل
    0.07
    疗效
    0.07
    onso
    0.07
    られています
    0.07
    рез
    0.07
    .BO
    0.07
     Gauge
    0.07
    时限
    0.07
    Activations Density 0.009%

    No Known Activations