© 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. 22340
    Prev
    Next
    INDEX
    Explanations

    parakeratosis, heterogeneity, argument, Tuesday

    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
    inous
    -0.07
    ÑĴ
    -0.07
    cipt
    -0.07
    ivor
    -0.06
    以ä¸ĭæĺ¯å°ıç¼ĸ
    -0.06
    repos
    -0.06
    ucky
    -0.06
    ingang
    -0.06
    æľ±åħĥ
    -0.06
     eventualmente
    -0.06
    POSITIVE LOGITS
    æľ¬è´¨
    0.07
    æĸ¹éĿ¢
    0.07
    ÏĨÏĮ
    0.06
    aspers
    0.06
    顾åIJįæĢĿä¹ī
    0.06
    ição
    0.06
    åĪĻéľĢè¦ģ
    0.06
    Ñijм
    0.06
    amer
    0.06
    mu
    0.06
    Activations Density 0.028%

    No Known Activations