© 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. 47295
    Prev
    Next
    INDEX
    Explanations

    ARM rot, OPT Extension, slow-paced

    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
    uille
    -0.06
    jenigen
    -0.06
    osis
    -0.06
    venuto
    -0.06
    osit
    -0.06
    åĭĩå¾Ģ缴åīį
    -0.06
    unami
    -0.06
    пÑı
    -0.06
    ncio
    -0.06
    \xff
    -0.06
    POSITIVE LOGITS
    ivan
    0.09
     Sicht
    0.07
    hest
    0.07
    erder
    0.07
    Stud
    0.07
    bord
    0.07
    enom
    0.07
    (arguments
    0.06
    гоÑĢа
    0.06
    Sheet
    0.06
    Activations Density 1.383%

    No Known Activations