© 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. 21282
    Prev
    Next
    INDEX
    Explanations

    questions that require answers

    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
    urga
    -0.08
    InParameter
    -0.08
    avig
    -0.08
    _MALLOC
    -0.08
    loys
    -0.07
     Ñģло
    -0.07
    å¢ŀæķĪ
    -0.07
    uff
    -0.07
    ZR
    -0.07
    stra
    -0.07
    POSITIVE LOGITS
    请çĶ¨
    0.07
    请填åĨĻ
    0.07
    mig
    0.07
    åĪ°ä½ł
    0.07
    åľ¨æŃ¤æ¬¡
    0.07
    åĨĻåĩº
    0.06
    è¯·åľ¨
    0.06
    quiz
    0.06
    åĽŀçŃĶéĹ®é¢ĺ
    0.06
     Hint
    0.06
    Activations Density 0.138%

    No Known Activations