© 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. 41362
    Prev
    Next
    INDEX
    Explanations

    amino compounds

    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
    enhagen
    -0.08
     Damn
    -0.07
    ynthia
    -0.07
    ÑĪний
    -0.07
    éĿ³
    -0.07
    ERV
    -0.07
    ly
    -0.06
    èŃ¦ç¤ºæķĻèĤ²
    -0.06
    upid
    -0.06
     recal
    -0.06
    POSITIVE LOGITS
    FINITY
    0.10
    adol
    0.09
    /octet
    0.09
    oyer
    0.09
    agara
    0.08
    ackbar
    0.08
    ÙĪدة
    0.08
    æĴ²
    0.08
    apur
    0.08
    leted
    0.08
    Activations Density 0.017%

    No Known Activations