© 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. 51131
    Prev
    Next
    INDEX
    Explanations

    et al. citations

    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
    稽
    -0.09
    åĬ¨å¼¹
    -0.08
    berto
    -0.07
    ibold
    -0.07
    UGH
    -0.07
    igator
    -0.06
    его
    -0.06
    åĨ°åĩī
    -0.06
    anford
    -0.06
    chie
    -0.06
    POSITIVE LOGITS
     contributor
    0.07
    lina
    0.07
    åºŁçī©
    0.07
    ilet
    0.07
    step
    0.07
    #:
    0.07
     https
    0.07
    roj
    0.07
    веÑĢа
    0.06
    é½Ĭ
    0.06
    Activations Density 0.187%

    No Known Activations