© 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. 9369
    Prev
    Next
    INDEX
    Explanations

    n-bit or m-stage

    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
    åĨįæİ¥åĨį
    -0.08
    inho
    -0.07
    elaar
    -0.07
    upati
    -0.07
    åIJĦè¡Į
    -0.06
    Various
    -0.06
     tuá»ķi
    -0.06
    ä¸ĩæĴŃæĶ¾
    -0.06
    æľĪåı·
    -0.06
    λοί
    -0.06
    POSITIVE LOGITS
    icen
    0.08
    ëłģ
    0.07
    unde
    0.07
    ilé
    0.07
    ewire
    0.07
    ë§Įíģ¼
    0.07
    ç½ij讯
    0.07
    _itr
    0.07
    ÃŃsticas
    0.07
     arras
    0.07
    Activations Density 0.014%

    No Known Activations