© 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. 40452
    Prev
    Next
    INDEX
    Explanations

    how to use words

    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
    å§ĶåĨħ
    -0.08
    åħ·
    -0.08
    ied
    -0.07
    åĴĮåĪ©çĶ¨
    -0.07
    ulumi
    -0.07
    Marshal
    -0.07
    ruik
    -0.06
    дÑĮми
    -0.06
     ops
    -0.06
     Orchard
    -0.06
    POSITIVE LOGITS
    _HOME
    0.08
    agos
    0.08
    èĥ¡æ¤Ĵ
    0.07
    isar
    0.07
    zem
    0.07
    æĦĪ
    0.07
    ãģŁãĤĭ
    0.07
    tral
    0.07
    .IS
    0.07
    æŶéĹ´æĺ¯
    0.07
    Activations Density 0.009%

    No Known Activations