© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 40253
    Prev
    Next
    INDEX
    Explanations

    partner violence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urry
    -0.07
    ~
    -0.07
    zl
    -0.07
    æ¯ĶæѦ
    -0.06
    auj
    -0.06
    æīİåħĭ
    -0.06
    ITI
    -0.06
     Harbor
    -0.06
    agal
    -0.06
    Run
    -0.06
    POSITIVE LOGITS
    keen
    0.09
    å¿ĥå¦Ĥ
    0.08
    å®
    0.08
    ÑĢанже
    0.07
    Severity
    0.07
     squared
    0.07
    stderr
    0.07
    waan
    0.07
    DOMNode
    0.07
    GetType
    0.07
    Activations Density 0.001%

    No Known Activations