© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26885
    Prev
    Next
    INDEX
    Explanations

    catalyzing, blocking, effect, operative, conditioning

    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
    ä¹ĭ大
    -0.08
    1
    -0.08
    ija
    -0.07
    anguage
    -0.07
    اÙĭ
    -0.07
    \_
    -0.07
    ä¹ĭæīĢ
    -0.07
     Ñģобой
    -0.07
    ä¹ĭé£İ
    -0.07
    -
    -0.07
    POSITIVE LOGITS
    raries
    0.14
    ä¸įåı¯æĢĿè®®
    0.14
    gether
    0.14
    身临åħ¶å¢ĥ
    0.13
    åĭĩå¾Ģ缴åīį
    0.11
    iculty
    0.11
    äºĭåįĬåĬŁåĢį
    0.11
    en
    0.11
    èĢ³çĨŁèĥ½è¯¦
    0.11
    æĸ°åĬłåĿ¡
    0.10
    Activations Density 1.076%

    No Known Activations