© 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. 18602
    Prev
    Next
    INDEX
    Explanations

    historical figures and names

    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
    whereIn
    -0.08
    èł
    -0.08
    andia
    -0.07
    æľ¬ç«ĻæīĢæľī
    -0.07
    гей
    -0.07
    abria
    -0.07
    è°Ĩ
    -0.07
    ibal
    -0.07
    alker
    -0.07
    æĨ¬
    -0.07
    POSITIVE LOGITS
    åIJİèĩ³
    0.07
    rh
    0.07
    emet
    0.07
    chs
    0.07
    å¸Ĥåľºåıijå±ķ
    0.06
    ugat
    0.06
    nek
    0.06
     anecd
    0.06
    eci
    0.06
    OURS
    0.06
    Activations Density 0.002%

    No Known Activations