© 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. 49204
    Prev
    Next
    INDEX
    Explanations

    keratein

    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
    åĪ©
    -0.07
    ÙĪارÙĩ
    -0.07
    æĺıè¿·
    -0.07
    fac
    -0.06
     Nel
    -0.06
    è´
    -0.06
    ãģĮãĤĵ
    -0.06
    continuous
    -0.06
    voj
    -0.06
    aro
    -0.06
    POSITIVE LOGITS
    ä¼įå¾·
    0.07
    Destructor
    0.07
    aths
    0.07
    çļĩåŃIJ
    0.06
    adena
    0.06
    ÙĦØ©
    0.06
     Unt
    0.06
    ä¸Ńé«ĺ
    0.06
    inant
    0.06
    oda
    0.06
    Activations Density 1.060%

    No Known Activations