© 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. 37930
    Prev
    Next
    INDEX
    Explanations

    care about

    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
    (?)
    -0.07
    elson
    -0.07
     '
    -0.06
     (?)
    -0.06
    ·
    -0.06
    ondrous
    -0.06
    è¿ĩåİ»
    -0.06
    æ£Ģ
    -0.06
    ?(
    -0.06
    å·¥ä½ľåľ¨
    -0.06
    POSITIVE LOGITS
    traits
    0.09
    âĢij
    0.09
    zuki
    0.09
    halts
    0.08
    üz
    0.08
    pees
    0.08
    _CSR
    0.08
    âĢ¦*
    0.08
    éĢģä¸Ģ
    0.08
    ).-
    0.08
    Activations Density 0.039%

    No Known Activations