© 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. 34105
    Prev
    Next
    INDEX
    Explanations

    value and 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
    etros
    -0.08
    ampur
    -0.08
    çĿ¦
    -0.08
     targ
    -0.08
    è¡·
    -0.07
    adium
    -0.07
    station
    -0.07
    acson
    -0.07
    åı¯èĥ½åŃĺåľ¨
    -0.07
    Expressions
    -0.07
    POSITIVE LOGITS
     contribution
    0.10
    è´¡çĮ®
    0.09
    计åħ¥
    0.09
     contributed
    0.09
     Contribution
    0.08
     contribute
    0.08
    é¢Ŀå¤ĸçļĦ
    0.08
     contributes
    0.08
    计
    0.07
     contributing
    0.07
    Activations Density 0.011%

    No Known Activations