© 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. 42673
    Prev
    Next
    INDEX
    Explanations

    find nearest or next item

    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
    约车
    -0.08
    éħ¸çĶľ
    -0.07
     assorted
    -0.07
    /misc
    -0.06
    åĪ©æ¶¦æĢ»é¢Ŀ
    -0.06
    çIJIJç¢İ
    -0.06
    å¦Īå¦Ī们
    -0.06
     roda
    -0.06
    éĽĨä¸Ńç²¾åĬĽ
    -0.06
    è¥
    -0.06
    POSITIVE LOGITS
     ближай
    0.10
    çªģãģį
    0.08
    atea
    0.08
     nearest
    0.07
    ç»ĵæŀľè¡¨æĺİ
    0.07
    .hasNext
    0.07
     terdekat
    0.07
    _FOUND
    0.07
    -found
    0.07
     najbliż
    0.07
    Activations Density 0.006%

    No Known Activations