© 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. 65139
    Prev
    Next
    INDEX
    Explanations

    i = or x \

    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
    imonial
    -0.06
    åħ¶
    -0.06
    ·
    -0.06
    p
    -0.06
    ↵
    -0.06
     ((
    -0.05
    ť
    -0.05
    eur
    -0.05
    ((
    -0.05
     (
    -0.05
    POSITIVE LOGITS
    åIJ«éĩij
    0.09
    wis
    0.08
     PROGMEM
    0.08
    utine
    0.08
    ;amp
    0.08
    ours
    0.08
    embe
    0.08
    èĩªå·±
    0.08
    çļĦè¿Ļç§į
    0.08
    UNUSED
    0.08
    Activations Density 0.003%

    No Known Activations