© 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. 39301
    Prev
    Next
    INDEX
    Explanations

    step based

    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
    erweise
    -0.09
    èįīæľ¨
    -0.09
    erdale
    -0.09
    ighting
    -0.09
    plicht
    -0.09
    enticator
    -0.09
    åłĤçļĩ
    -0.09
     ÑĤÑĢÑĥда
    -0.09
    schaft
    -0.08
    enticate
    -0.08
    POSITIVE LOGITS
    wise
    0.12
    骤
    0.11
    lessly
    0.09
    ä¹ĭéģ¥
    0.08
    less
    0.08
    andard
    0.08
    é©Ł
    0.08
    ed
    0.07
    tern
    0.07
    weise
    0.07
    Activations Density 0.046%

    No Known Activations