© 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. 28163
    Prev
    Next
    INDEX
    Explanations

    izumi

    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
    æľī家
    -0.07
    riba
    -0.07
    åį³åĪ°
    -0.06
    haus
    -0.06
    maan
    -0.06
    bai
    -0.06
    ç®ķ
    -0.06
    razi
    -0.06
    å©ķ
    -0.06
     house
    -0.06
    POSITIVE LOGITS
    acker
    0.08
    æµ·æ£ł
    0.07
    åľ¨æŃ¤åŁºç¡Ģä¸Ĭ
    0.07
    ÑĢез
    0.07
    irit
    0.07
    itzer
    0.07
    åħ¬åĽŃéĩĮ
    0.07
    å¥Ķ
    0.06
    nehmer
    0.06
     Chore
    0.06
    Activations Density 0.011%

    No Known Activations