© 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. 2114
    Prev
    Next
    INDEX
    Explanations

    math factors

    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
    大å°ıå§IJ
    -0.08
     fflush
    -0.07
    ãĤ¥
    -0.07
     bách
    -0.07
    å«ĮçĬ¯
    -0.07
     депÑĥÑĤаÑĤÑĭ
    -0.07
    >-
    -0.07
    鼶ä¸ĭ
    -0.07
    leiding
    -0.07
    contin
    -0.07
    POSITIVE LOGITS
    åĽłåŃIJ
    0.10
    -factor
    0.10
     factor
    0.09
    åĢįæķ°
    0.09
     Factor
    0.09
    åĢįçļĦ
    0.09
    _FACTOR
    0.08
    _factor
    0.08
    åĢį
    0.08
     factors
    0.08
    Activations Density 0.003%

    No Known Activations