© 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. 8504
    Prev
    Next
    INDEX
    Explanations

    TGF-beta prefixes or suffixes

    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
    uitar
    -0.06
    amate
    -0.06
    rzy
    -0.06
    à»
    -0.06
    çIJĨ论ä¸İ
    -0.06
    .hm
    -0.06
    ç§ijåѦä¸İ
    -0.06
    shire
    -0.06
    arie
    -0.06
    .mid
    -0.06
    POSITIVE LOGITS
    ENN
    0.09
    acho
    0.08
    aky
    0.07
    ":""
    0.07
    pected
    0.07
    _PORTS
    0.07
    OfString
    0.07
    letz
    0.07
    lap
    0.07
    åŃIJæĺ¯
    0.07
    Activations Density 0.002%

    No Known Activations