© 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. 30847
    Prev
    Next
    INDEX
    Explanations

    extract or cut

    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
    ambah
    -0.07
    _PROVID
    -0.07
    adesh
    -0.07
    edenk
    -0.07
     rep
    -0.06
    שת
    -0.06
    arci
    -0.06
     przew
    -0.06
    Rep
    -0.06
     reps
    -0.06
    POSITIVE LOGITS
     extracting
    0.19
     extraction
    0.19
    æıIJåıĸ
    0.18
     Extraction
    0.17
    extract
    0.17
    .extract
    0.17
     extracted
    0.16
     extracts
    0.16
     extract
    0.16
     Extract
    0.16
    Activations Density 0.199%

    No Known Activations