© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26773
    Prev
    Next
    INDEX
    Explanations

    pull request or issue

    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
    ptico
    -0.07
    تر
    -0.07
    æīĭæĦŁ
    -0.07
    èħ¾è®¯å¾®åįļ
    -0.07
    æĥ³çŁ¥éģĵçļĦçŃĶæ¡Ī
    -0.07
    å¢
    -0.07
    éĩij森
    -0.06
    åħ¨æľ¬å°ı说
    -0.06
    opard
    -0.06
    éĩijèĬ±
    -0.06
    POSITIVE LOGITS
    bern
    0.07
    æĺµ
    0.07
    apiro
    0.07
    _changes
    0.07
    ubar
    0.07
    #:
    0.07
    arna
    0.07
    ëĭ¥
    0.07
    itle
    0.07
    air
    0.06
    Activations Density 0.002%

    No Known Activations