© 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. 45160
    Prev
    Next
    INDEX
    Explanations

    trailing whitespace

    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
     rac
    -0.07
     familiar
    -0.07
     favorable
    -0.06
    μÎŃν
    -0.06
    umus
    -0.06
    âĢ
    -0.06
    Ãłm
    -0.06
    MENT
    -0.06
    ÃĹ
    -0.06
    ánchez
    -0.06
    POSITIVE LOGITS
    <|fim_suffix|>
    0.09
     diserta
    0.08
    就差
    0.08
     Ejem
    0.08
    sos
    0.08
    绵
    0.07
     escorte
    0.07
     korpor
    0.07
    inator
    0.07
    Vien
    0.07
    Activations Density 0.199%

    No Known Activations