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. 15-RESID-POST-AA
    6. 13796
    Prev
    Next
    INDEX
    Explanations

    lever

    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
     pageIndex
    -0.08
     rhs
    -0.07
     matte
    -0.07
     وزارة
    -0.07
    uj
    -0.07
     Expected
    -0.07
    .Framework
    -0.07
    IGIN
    -0.07
     predicate
    -0.07
     beams
    -0.07
    POSITIVE LOGITS
    _gc
    0.07
    扶
    0.07
    _sep
    0.07
    FormData
    0.07
    volução
    0.07
    🍻
    0.07
    'al
    0.07
     współpr
    0.06
    엌
    0.06
     shaking
    0.06
    Activations Density 0.021%

    No Known Activations