© 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. 12924
    Prev
    Next
    INDEX
    Explanations

    suffix or end of words

    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
    åĪĺçķħ
    -0.09
    åıĮé±¼
    -0.08
    akaran
    -0.08
    _membership
    -0.08
    å¹³éĺ³
    -0.08
    <|box_end|>
    -0.08
    å¾·åŁº
    -0.08
    åĭī强
    -0.08
    è·¨çķĮ
    -0.08
    åı¯æĢľ
    -0.07
    POSITIVE LOGITS
     identical
    0.08
     repl
    0.07
    ident
    0.07
     restart
    0.07
     reset
    0.07
    就好åĥı
    0.07
     ident
    0.07
     resets
    0.07
     restarted
    0.07
     بÙĨÙģس
    0.07
    Activations Density 0.006%

    No Known Activations