© 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. 13035
    Prev
    Next
    INDEX
    Explanations

    here to

    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
     hereby
    -0.09
    orsk
    -0.09
     thereby
    -0.08
    ÑģÑı
    -0.08
    çIJĨå·¥åѦéĻ¢
    -0.08
    nya
    -0.08
    orsi
    -0.08
    <|box_end|>
    -0.08
    ors
    -0.08
    ebene
    -0.07
    POSITIVE LOGITS
    abouts
    0.22
    after
    0.10
    ãģĺãĤģãģ¦
    0.10
    adays
    0.10
    -même
    0.10
    ìłĢ
    0.09
    zul
    0.08
    upon
    0.08
    Å¡nj
    0.08
     mismo
    0.08
    Activations Density 0.118%

    No Known Activations