© 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. 12757
    Prev
    Next
    INDEX
    Explanations

    ectopic, Hawkes, Cortana, Hellinger, Apgar, honeycomb, katakana, ADSL, Fabry

    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
    ª½
    -0.08
    è¿Ļ个éĺ¶æ®µ
    -0.07
    ouncer
    -0.07
    chées
    -0.06
    æ¡ĤåĽŃ
    -0.06
    trang
    -0.06
    trer
    -0.06
    ои
    -0.06
    åĽłæĸ¯åĿ¦
    -0.06
    è¶ħä¹İ
    -0.06
    POSITIVE LOGITS
    ember
    0.08
    oll
    0.07
    ئ
    0.07
    ÅĽÄĩ
    0.07
    bridge
    0.07
    uell
    0.07
    صÙģ
    0.07
    ellar
    0.06
    大åݨ
    0.06
    بد
    0.06
    Activations Density 1.383%

    No Known Activations