© 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. 57335
    Prev
    Next
    INDEX
    Explanations

    level or concentration

    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
    åİĦ
    -0.08
    .cc
    -0.07
    æ²Ľ
    -0.07
     érett
    -0.07
    伯çĪµ
    -0.07
    çģ«çĥŃçļĦ
    -0.07
     ATTRIBUTE
    -0.07
    asso
    -0.07
    è¶Ĭèµ°è¶Ĭ
    -0.07
    _scaling
    -0.06
    POSITIVE LOGITS
    ç»´æĮģåľ¨
    0.10
    æijĩ
    0.09
    ä¿ĿæĮģåľ¨
    0.09
    æ³¢æ¾ľ
    0.08
    ç»´æĮģ
    0.08
    æ³¢åĬ¨
    0.08
    æ³¢åĭķ
    0.08
    istar
    0.08
    åįĩèĩ³
    0.07
     steady
    0.07
    Activations Density 0.097%

    No Known Activations