© 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. 19404
    Prev
    Next
    INDEX
    Explanations

    Rabin-Karp Quick-verify Computing

    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
     dist
    -0.07
    代表äºĨ
    -0.07
    åĪĨéħį
    -0.06
    زÙĬØ©
    -0.06
     Sears
    -0.06
    天干
    -0.06
     feed
    -0.06
    ä¸ĵæŁľ
    -0.06
    åħħ满çĿĢ
    -0.06
    累累
    -0.06
    POSITIVE LOGITS
     probabil
    0.08
    æ¦Ĥçİĩ
    0.08
     Cheap
    0.08
    Cheap
    0.08
    detect
    0.08
    .Verify
    0.07
    gur
    0.07
     randomized
    0.07
    ixture
    0.07
    _verify
    0.07
    Activations Density 0.008%

    No Known Activations