© 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. 32095
    Prev
    Next
    INDEX
    Explanations

    furnace

    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
    киÑĪе
    -0.10
    ASCADE
    -0.08
    понен
    -0.08
    еÑĢбÑĥ
    -0.07
    abbage
    -0.07
    нома
    -0.07
    каÑĤеÑĢи
    -0.07
    движи
    -0.07
    mong
    -0.07
    zinha
    -0.07
    POSITIVE LOGITS
    ±
    0.08
    วย
    0.07
    ijin
    0.07
    ouch
    0.07
    è·¯ä¸İ
    0.07
    Ĵ
    0.07
    ibri
    0.07
    ²
    0.06
    akit
    0.06
    æŶåħī
    0.06
    Activations Density 1.155%

    No Known Activations