© 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. 49302
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    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
    è¿ĶåĽŀ顶éĥ¨
    -0.07
    omb
    -0.07
    æ£ļ
    -0.07
    åħ¬å¹³åħ¬æŃ£
    -0.07
    è¦
    -0.06
    /INFO
    -0.06
    μÎŃ
    -0.06
    IMIZE
    -0.06
    orr
    -0.06
    нин
    -0.06
    POSITIVE LOGITS
    []"
    0.08
    estu
    0.07
    æĺ¯åIJĹ
    0.07
    ady
    0.07
    idet
    0.07
    ï¼ģï¼Ī
    0.07
    _authentication
    0.07
     correc
    0.06
    flo
    0.06
    è¾Ľèĭ¦äºĨ
    0.06
    Activations Density 0.002%

    No Known Activations