© 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. 55543
    Prev
    Next
    INDEX
    Explanations

    quantities after numbers

    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
    çİ
    -0.07
    пно
    -0.07
    å¥
    -0.06
    RAFT
    -0.06
    åĮºåĿĹ
    -0.06
    னà¯įப
    -0.06
    agno
    -0.06
    籤
    -0.06
    ides
    -0.06
    udem
    -0.06
    POSITIVE LOGITS
    whose
    0.09
     whose
    0.09
    并对åħ¶
    0.08
    åıĬåħ¶
    0.08
    æīĢ带æĿ¥çļĦ
    0.08
     Enumerator
    0.08
    计
    0.07
    ãģ«ãģĭãģĭãĤĭ
    0.07
     cuya
    0.07
    ä¸ĭåľº
    0.07
    Activations Density 0.159%

    No Known Activations