© 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. 55895
    Prev
    Next
    INDEX
    Explanations

    description of specific noun phrases

    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
    è¯ģåĪ¸äº¤æĺĵæīĢ
    -0.07
    allah
    -0.06
    (___
    -0.06
    umpa
    -0.06
    aded
    -0.06
    asal
    -0.06
    dde
    -0.06
    [__
    -0.06
    éĩįçĸ¾
    -0.06
    æ¯Ķä¸ĺ
    -0.06
    POSITIVE LOGITS
    ,...
    0.11
     [âĢ¦]
    0.11
    ,âĢ¦
    0.10
     [...]
    0.10
     ...
    0.10
     (...)
    0.10
    Dettagli
    0.08
    .âĢ¦
    0.08
    ↵↵
    0.08
    "...
    0.07
    Activations Density 11.206%

    No Known Activations