© 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. 55316
    Prev
    Next
    INDEX
    Explanations

    = prefix

    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
     ì¹ĺ
    -0.08
    isar
    -0.08
    amet
    -0.07
    ytu
    -0.07
     bals
    -0.07
    ä¼ij
    -0.07
    erb
    -0.07
    åĨ²åĩ»
    -0.07
    _refl
    -0.07
    å¯¹æľ¬æ¬¡
    -0.07
    POSITIVE LOGITS
    endorf
    0.08
    amiliar
    0.07
    onaut
    0.07
    elle
    0.07
    mann
    0.07
    使åħ¶
    0.07
    æ²Ľ
    0.07
    ä¸Ģéģĵéģĵ
    0.06
     Pins
    0.06
    éĢģåĽŀ
    0.06
    Activations Density 0.007%

    No Known Activations