© 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. 51721
    Prev
    Next
    INDEX
    Explanations

    last name followed by specific title/role

    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
    _specs
    -0.07
    ç»Īäºİ
    -0.07
    让æĪij
    -0.07
    ingkatan
    -0.07
    ²
    -0.07
    vestig
    -0.07
     unavoid
    -0.07
     cutoff
    -0.06
    精讲
    -0.06
     hairy
    -0.06
    POSITIVE LOGITS
    cela
    0.08
     ::=
    0.08
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.08
    åı¯éĿłçļĦ
    0.07
    ä¸įç´Ĭ
    0.07
    ]-$
    0.07
    æ¡Ī
    0.07
    μάÏĦÏīν
    0.07
    deb
    0.07
    åı¯éĿł
    0.06
    Activations Density 0.001%

    No Known Activations