© 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. 28908
    Prev
    Next
    INDEX
    Explanations

    forcing language

    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
    -0.07
    ed
    -0.06
     peri
    -0.06
    ilor
    -0.06
    -
    -0.06
    ↵
    -0.06
    æł¸ç®Ĺ
    -0.06
     magn
    -0.06
     il
    -0.06
     Jep
    -0.06
    POSITIVE LOGITS
     Grosso
    0.10
    .shuffle
    0.09
    fluss
    0.09
    éĵ¶å±±
    0.08
    umph
    0.08
    asure
    0.08
    egel
    0.08
    аÑĤо
    0.08
    ukti
    0.08
     scomp
    0.08
    Activations Density 0.009%

    No Known Activations