© 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. 24999
    Prev
    Next
    INDEX
    Explanations

    mathematical derivatives and fractions

    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
    ł
    -0.08
    ebet
    -0.07
    ç¾ģ
    -0.07
    tees
    -0.07
     ancestor
    -0.07
    .binary
    -0.07
    ücke
    -0.07
     Bark
    -0.07
    æļĹå¤ľ
    -0.06
    åłħ
    -0.06
    POSITIVE LOGITS
     cresc
    0.07
     quadratic
    0.07
    ä¸ĩåį·
    0.07
    odon
    0.07
    çĶĺéľ²
    0.07
    adratic
    0.07
    Launch
    0.07
    çĥĤ漫
    0.07
    ä»İ鼶
    0.07
    /forms
    0.07
    Activations Density 0.006%

    No Known Activations