© 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. 62261
    Prev
    Next
    INDEX
    Explanations

    numbers, punctuation, and UDP

    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
    retto
    -0.08
    rys
    -0.07
    _MISC
    -0.06
    {}.
    -0.06
    pery
    -0.06
    è¿ĻçĤ¹
    -0.06
    æľ«
    -0.06
    esso
    -0.06
     Eliz
    -0.06
    ledes
    -0.06
    POSITIVE LOGITS
    ovol
    0.08
    önen
    0.08
    ToDelete
    0.08
    بÙĪد
    0.07
    toi
    0.07
    gom
    0.07
    erra
    0.07
    æĽ´æĸ°æĹ¥æľŁ
    0.07
    çŃīçŃī
    0.07
    ä¿¡æģ¯çŃī
    0.07
    Activations Density 0.076%

    No Known Activations