© 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. 39847
    Prev
    Next
    INDEX
    Explanations

    programming 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
    toHaveLength
    -0.07
    raul
    -0.06
    annes
    -0.06
    ingle
    -0.06
    æĻĵ
    -0.06
    cesa
    -0.06
    åĴ«
    -0.06
    {'
    -0.06
    à
    -0.06
     Wake
    -0.06
    POSITIVE LOGITS
    éģĩè§ģä½ł
    0.08
    uzzle
    0.07
    stech
    0.07
    uÄĩ
    0.07
    ulangan
    0.07
    æĺ¯ä½łä»¬
    0.07
    racji
    0.07
    ุà¹Īà¸Ļ
    0.07
     beker
    0.07
    leftright
    0.06
    Activations Density 0.015%

    No Known Activations