© 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. 48100
    Prev
    Next
    INDEX
    Explanations

    dosimeters or dose

    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
    è¸
    -0.06
    ↵
    -0.06
    iri
    -0.06
    ak
    -0.06
    bol
    -0.06
    irit
    -0.06
    åŀ£
    -0.06
     bol
    -0.05
    çıł
    -0.05
    \
    -0.05
    POSITIVE LOGITS
    atest
    0.08
    teis
    0.08
    æķ¬è¯·
    0.08
    Ïįν
    0.08
    tps
    0.08
    èĭ±æĸĩåIJįåŃĹ
    0.08
    édi
    0.08
    ÄĻt
    0.08
    adiens
    0.08
    stech
    0.07
    Activations Density 0.001%

    No Known Activations