© 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. 15-RESID-POST-AA
    6. 27118
    Prev
    Next
    INDEX
    Explanations

    into

    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
    .crm
    -0.07
    getKey
    -0.07
    ycles
    -0.07
    vehicle
    -0.07
     shops
    -0.07
     PSU
    -0.07
    به
    -0.07
    外围
    -0.07
    ㅓ
    -0.06
    capacity
    -0.06
    POSITIVE LOGITS
     nghị
    0.08
    .al
    0.08
    _BOOLEAN
    0.07
    .Validation
    0.07
    Evaluation
    0.07
    再造
    0.07
    .pull
    0.07
     ArgumentException
    0.06
     uniq
    0.06
     ثلاثة
    0.06
    Activations Density 0.020%

    No Known Activations