© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4555
    Prev
    Next
    INDEX
    Explanations

    miles long

    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
    让èĩªå·±çļĦ
    -0.07
    çĶļèĩ³è¿ĺ
    -0.06
    åĽłä¸ºæĪij
    -0.06
    çĶļèĩ³æĺ¯
    -0.06
    ç»Ħç»Ħéķ¿
    -0.06
    åĽłä¸ºåħ¶
    -0.06
    æĪĸåħ¶å®ĥ
    -0.06
    åĽłä¸ºè¿Ļ
    -0.06
    azan
    -0.06
    åĽłä¸ºåľ¨
    -0.06
    POSITIVE LOGITS
    <|box_end|>
    0.07
    建åĪ¶
    0.07
    icone
    0.06
    æľĿ
    0.06
    inkt
    0.06
     mó
    0.06
    çļĭ
    0.06
     Tore
    0.06
    .ContentType
    0.06
    .freeze
    0.06
    Activations Density 0.012%

    No Known Activations