© 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. 38179
    Prev
    Next
    INDEX
    Explanations

    assignment or declaration

    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
    çĽ¸çŁ¥
    -0.08
    ssi
    -0.08
    armo
    -0.07
    _ENCODING
    -0.07
    niÄį
    -0.07
    ersen
    -0.07
    èĴĤ
    -0.07
    adel
    -0.07
    åºıåı·
    -0.07
     regelmatig
    -0.07
    POSITIVE LOGITS
    éľĢæ±ĤçļĦ
    0.07
     demanded
    0.07
     necessity
    0.07
    emand
    0.07
     demanding
    0.07
    æĺİç¡®è¦ģæ±Ĥ
    0.07
    Demand
    0.07
     необÑħодим
    0.07
     liquor
    0.07
    ä¸īåı£
    0.06
    Activations Density 0.003%

    No Known Activations