© 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. 27735
    Prev
    Next
    INDEX
    Explanations

    ": or "

    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
    ity
    -0.07
    ãĢĢãĢĢ
    -0.06
    åѦæ³ķ
    -0.06
    owell
    -0.06
    anter
    -0.06
    åıĤä¸İè¯Ħ论
    -0.06
    æµ·éģĵ
    -0.06
     Proud
    -0.06
    оÑĤно
    -0.06
     *_
    -0.06
    POSITIVE LOGITS
    ##_
    0.08
    Ĺı
    0.08
    ãĢĬ
    0.07
    à¨Ĥ
    0.07
    âĢĮ
    0.07
    _whitespace
    0.07
    ahkan
    0.07
    à¯įப
    0.07
    áŀ»áŀĦ
    0.07
     diserta
    0.07
    Activations Density 0.309%

    No Known Activations