Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 36575
    Prev
    Next
    INDEX
    Explanations

    legal exceptions and rules

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _where
    -0.08
    iculos
    -0.07
    -xs
    -0.07
    也曾
    -0.07
    .utcnow
    -0.07
    ')")↵
    -0.07
     approximation
    -0.07
    .port
    -0.06
     Buf
    -0.06
     pharmac
    -0.06
    POSITIVE LOGITS
     Raq
    0.07
     impaired
    0.07
     pyplot
    0.07
    icker
    0.06
    火箭
    0.06
    _UPDATED
    0.06
    产业基地
    0.06
     Instance
    0.06
    יך
    0.06
     Qualified
    0.06
    Activations Density 0.001%

    No Known Activations