© 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. 56172
    Prev
    Next
    INDEX
    Explanations

    two points

    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
     berk
    -0.08
    ardon
    -0.08
    bed
    -0.08
     пÑĢодÑĥ
    -0.08
    beren
    -0.08
    azy
    -0.08
    unbind
    -0.07
    ENTO
    -0.07
    orch
    -0.07
    交æµģä¸İ
    -0.07
    POSITIVE LOGITS
    ç¨įæľī
    0.09
    çķ¥æľī
    0.09
    çķ¥å¾®
    0.08
    çķ¥
    0.08
     slightly
    0.08
     slight
    0.08
    å®Įç¾İçļĦ
    0.08
     minor
    0.08
    ç¨įç¨į
    0.08
     perfect
    0.08
    Activations Density 0.233%

    No Known Activations