© 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. 60932
    Prev
    Next
    INDEX
    Explanations

    colons and identifiers

    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
    esel
    -0.07
    ubin
    -0.07
    esk
    -0.07
    åĿª
    -0.07
    ussian
    -0.07
    ey
    -0.07
    arvi
    -0.06
    üssel
    -0.06
    avid
    -0.06
     UNICODE
    -0.06
    POSITIVE LOGITS
    akis
    0.08
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.08
    trad
    0.07
    串
    0.07
    bolo
    0.07
    <|im_start|>
    0.07
     another
    0.07
    ãĢĤwww
    0.06
    åĵªäºĽéĹ®é¢ĺ
    0.06
     {*}
    0.06
    Activations Density 1.072%

    No Known Activations