© 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. 56670
    Prev
    Next
    INDEX
    Explanations

    viewing our boards

    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
    slt
    -0.09
    agt
    -0.08
    ehl
    -0.08
    usak
    -0.08
    å°½
    -0.08
    å°½æľī
    -0.08
    ä¸įä¹°
    -0.07
    ureka
    -0.07
    ighton
    -0.07
    ä¸Ģ念
    -0.07
    POSITIVE LOGITS
    erbe
    0.07
    inary
    0.07
    _INLINE
    0.06
     Sonn
    0.06
    éĤĢ
    0.06
    缮åīįæŃ£åľ¨
    0.06
    æ¡£
    0.06
     suicides
    0.06
    witter
    0.06
    TREE
    0.06
    Activations Density 0.191%

    No Known Activations