© 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. 34296
    Prev
    Next
    INDEX
    Explanations

    I followed by specific abbreviations

    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
    s
    -0.11
    ä½Ĩä¸įéĻIJäºİ
    -0.10
    schild
    -0.09
    lah
    -0.09
    ned
    -0.08
    ات
    -0.07
    лÑĭй
    -0.07
    nya
    -0.07
    idency
    -0.07
    nable
    -0.07
    POSITIVE LOGITS
    rvine
    0.17
    gnore
    0.12
     nærheten
    0.12
    annis
    0.11
    reland
    0.11
    zaak
    0.11
    ssue
    0.10
    perial
    0.10
    olated
    0.10
    brahim
    0.10
    Activations Density 0.625%

    No Known Activations