© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26762
    Prev
    Next
    INDEX
    Explanations

    faced by, taught to, walked into

    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
    åİ»åĵª
    -0.08
    oshi
    -0.07
    åħ¨éĿ¢è´¯å½»èIJ½å®ŀ
    -0.06
    ãģ¨ãģĦãģĨãģ®ãĤĤ
    -0.06
    лиÑĤа
    -0.06
    hom
    -0.06
    onga
    -0.06
    arz
    -0.06
    _PACKAGE
    -0.06
    öch
    -0.06
    POSITIVE LOGITS
    uis
    0.08
    stime
    0.08
    æķ°æį®çºłéĶĻ
    0.07
    /INFO
    0.07
    irro
    0.07
    beeld
    0.07
    [..
    0.07
    (ERR
    0.07
    \"
    0.06
    Encode
    0.06
    Activations Density 0.003%

    No Known Activations