© 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. 61184
    Prev
    Next
    INDEX
    Explanations

    control of prevention

    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
    ibu
    -0.07
    éŃ
    -0.07
    azaar
    -0.07
    ä¾Ŀ
    -0.07
    ä¾Ŀçħ§
    -0.06
    acz
    -0.06
    çłĶ究éĻ¢
    -0.06
    zcz
    -0.06
     Nobel
    -0.06
    è§ĨçªĹ
    -0.06
    POSITIVE LOGITS
    éĢļè¿ĩåIJĦç§į
    0.14
    诸å¦Ĥ
    0.13
     somehow
    0.13
     via
    0.12
    via
    0.12
    ä¾ĭå¦Ĥ
    0.11
     somew
    0.11
    èѬå¦Ĥ
    0.11
     berupa
    0.11
    æ¯Ķå¦Ĥåľ¨
    0.11
    Activations Density 0.528%

    No Known Activations