© 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. 58479
    Prev
    Next
    INDEX
    Explanations

    command line execution

    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
    veld
    -0.07
    daw
    -0.07
    icat
    -0.06
    Ïĥκ
    -0.06
    lot
    -0.06
     pitches
    -0.06
    _dem
    -0.06
    arani
    -0.06
    iterr
    -0.06
    ä¸ĩå²ģ
    -0.06
    POSITIVE LOGITS
     Ogg
    0.07
    ën
    0.07
     Münster
    0.07
    omen
    0.07
    Assembler
    0.06
    ãĥĭãĥ¼
    0.06
     Burst
    0.06
    escape
    0.06
    Escape
    0.06
    éĢ¸
    0.06
    Activations Density 0.491%

    No Known Activations