© 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. 14455
    Prev
    Next
    INDEX
    Explanations

    recurring dates

    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
     Harden
    -0.08
    .vel
    -0.07
    innie
    -0.07
    è®ĢæĽ¸
    -0.07
    .*?)
    -0.07
    erso
    -0.07
    uchte
    -0.07
    ÃijA
    -0.07
     ìĶ
    -0.07
    _scale
    -0.07
    POSITIVE LOGITS
    uet
    0.07
    linie
    0.07
    æľ¨åģ¶
    0.07
    á»ĩt
    0.07
    protobuf
    0.07
    uket
    0.07
    ablement
    0.07
    _STOP
    0.06
    åıĪä¸Ģ
    0.06
    æľīä¸ī个
    0.06
    Activations Density 0.002%

    No Known Activations