© 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. 20979
    Prev
    Next
    INDEX
    Explanations

    lumber

    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
    ×Ŀ
    -0.07
    æĹıèĩªæ²»åİ¿
    -0.07
    <tool_response>
    -0.06
    ï¸ı
    -0.06
    ère
    -0.06
    uide
    -0.06
     balas
    -0.06
    à°Łà°¿
    -0.06
    ists
    -0.06
    ilege
    -0.06
    POSITIVE LOGITS
    åIJİæĦŁ
    0.08
    ched
    0.08
    ...',
    0.08
    >>()
    0.08
    è§Ĵ度æĿ¥è¯´
    0.08
    QU
    0.08
    ÅĽc
    0.07
    çĶŁæķĪä¹ĭæĹ¥èµ·
    0.07
     ฯ
    0.07
    ÏħÏĩ
    0.07
    Activations Density 0.382%

    No Known Activations