© 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. 45708
    Prev
    Next
    INDEX
    Explanations

    asking how or what to explain

    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
    åĩºè®©
    -0.09
    ursal
    -0.08
     Tog
    -0.08
    olg
    -0.08
    .hashCode
    -0.08
    ogat
    -0.08
    !--
    -0.07
    ç»ĦåĽ¾
    -0.07
    udir
    -0.07
    indsight
    -0.07
    POSITIVE LOGITS
     why
    0.07
    æ¯ıä¸ĢæŃ¥
    0.07
    ify
    0.06
    å¦Ĥä½ķçĶ¨
    0.06
    spin
    0.06
     reasons
    0.06
    ivate
    0.06
    å¦Ĥä½ķéĢīæĭ©
    0.06
    why
    0.06
     Museums
    0.06
    Activations Density 0.059%

    No Known Activations