© 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. 33897
    Prev
    Next
    INDEX
    Explanations

    figure reference

    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
    ãģ§ãģĤãĤįãģĨ
    -0.07
    sic
    -0.06
    渡
    -0.06
    apus
    -0.06
    __
    -0.06
    leid
    -0.06
    με
    -0.06
    ream
    -0.06
    ucc
    -0.06
    ¹
    -0.06
    POSITIVE LOGITS
    seealso
    0.09
    éĻĦåĽ¾
    0.09
    Figure
    0.08
    è§ģåĽ¾
    0.08
     Fig
    0.08
    figure
    0.08
     figura
    0.08
     Figure
    0.08
    tahan
    0.08
    ä¸Ĭæ·»
    0.08
    Activations Density 0.058%

    No Known Activations