© 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. 32236
    Prev
    Next
    INDEX
    Explanations

    potential value

    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
    istenz
    -0.08
    è³½
    -0.07
    _EFFECT
    -0.07
     chic
    -0.07
     kultur
    -0.06
    termin
    -0.06
    éĹĬ
    -0.06
    ubar
    -0.06
    åĨ²è¿Ľ
    -0.06
    大çİĭ
    -0.06
    POSITIVE LOGITS
    èĩªåĬ¨çĶŁæĪIJ
    0.08
     génér
    0.07
    踪迹
    0.07
    lair
    0.07
     Belo
    0.07
    isFunction
    0.07
    å¾´
    0.07
    ä½İ声
    0.07
    å¼ĦèĻļ
    0.07
    _generate
    0.07
    Activations Density 0.002%

    No Known Activations