© 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. 18516
    Prev
    Next
    INDEX
    Explanations

    names with foreign endings

    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
    almaz
    -0.07
    åĺģ
    -0.07
    ëĤĺëĿ¼
    -0.07
    ê°Ĵ
    -0.07
    VRT
    -0.07
    yclopedia
    -0.06
    refour
    -0.06
    obuf
    -0.06
    izzle
    -0.06
    _APB
    -0.06
    POSITIVE LOGITS
    yage
    0.08
    keiten
    0.08
    ftware
    0.08
    midt
    0.07
    ÄŁlu
    0.07
    дзе
    0.07
    etje
    0.07
    åĬłæĭ¿å¤§
    0.07
    æŀĿèĬ±
    0.06
    çĪ½åı£
    0.06
    Activations Density 0.618%

    No Known Activations