© 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. 12823
    Prev
    Next
    INDEX
    Explanations

    stage development progression

    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
    flater
    -0.08
    teid
    -0.08
    te
    -0.08
    ìķµ
    -0.07
    ieee
    -0.07
    DRAM
    -0.07
    nell
    -0.07
    èĩªæѤ
    -0.07
    ace
    -0.06
    TypeID
    -0.06
    POSITIVE LOGITS
    段éļİ
    0.09
     grad
    0.08
    éĺ¶æ®µ
    0.08
    è¿ĽåĮĸ
    0.07
     apprent
    0.07
     ëĭ¨ê³Ħ
    0.07
    frog
    0.07
    jev
    0.07
     stages
    0.07
    à¹Ħลà¹Ī
    0.07
    Activations Density 0.707%

    No Known Activations