© 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. 31806
    Prev
    Next
    INDEX
    Explanations

    selections or options

    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
    æĹłæīĢè°ĵ
    -0.07
    åĩłå¤§
    -0.07
    ÏģÏħ
    -0.07
    ÐŁÐ¡
    -0.06
    ports
    -0.06
    è·¯éĢı
    -0.06
    æī¾åĽŀå¯Ĩçłģ
    -0.06
    enner
    -0.06
    scha
    -0.06
    è¿Ļä¸ĭ
    -0.06
    POSITIVE LOGITS
    utum
    0.08
    éĥ½åIJĪ
    0.07
    çŃīçŃī
    0.07
    è¾Ľ
    0.07
     enfin
    0.07
    ouses
    0.07
    åı¦
    0.07
    stown
    0.07
    åıĪå¦Ĥ
    0.07
     finally
    0.07
    Activations Density 0.238%

    No Known Activations