© 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. 17878
    Prev
    Next
    INDEX
    Explanations

    please see, refer, send, call, view

    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
    ials
    -0.11
    <|box_end|>
    -0.09
    dbuf
    -0.08
    iguez
    -0.08
    elaar
    -0.08
     osa
    -0.08
    .truth
    -0.08
    illary
    -0.08
    tare
    -0.08
    atlan
    -0.08
    POSITIVE LOGITS
    er
    0.07
    ëĿ¼ëıĦ
    0.07
    веÑĤ
    0.07
    æŁ¬
    0.07
    TING
    0.07
    ãģĹãĤĤ
    0.07
    AnimationFrame
    0.07
    æĹ©æĹ¥
    0.07
    orate
    0.06
    íŀĪ
    0.06
    Activations Density 0.088%

    No Known Activations