© 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. 10473
    Prev
    Next
    INDEX
    Explanations

    except zero, away from, value of

    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
    å±ĤéĿ¢çļĦ
    -0.06
    ÙĪرÙĪب
    -0.06
    å¾ij
    -0.06
    åºĦ
    -0.06
     consenting
    -0.06
     ÐĹаÑĩ
    -0.06
    汪æ´ĭ
    -0.06
    æĤī
    -0.06
     record
    -0.06
     Barr
    -0.06
    POSITIVE LOGITS
    egah
    0.08
    subclass
    0.07
    ãĢģãĢģãĢģ
    0.07
    endre
    0.07
    epass
    0.07
    ParameterValue
    0.07
    asley
    0.07
    кл
    0.07
    ymm
    0.07
     dä
    0.07
    Activations Density 0.013%

    No Known Activations