© 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. 47925
    Prev
    Next
    INDEX
    Explanations

    number or byte sequence

    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
     Banc
    -0.08
    fans
    -0.07
    eme
    -0.07
    amel
    -0.07
     Gard
    -0.07
    assar
    -0.07
    νοÏħ
    -0.07
    ÙĪÙħتر
    -0.07
    asan
    -0.07
    anker
    -0.06
    POSITIVE LOGITS
     Readonly
    0.07
    -Smith
    0.07
    ĸ
    0.07
    пло
    0.07
    ķ
    0.07
    abaj
    0.06
    ç»ĥ
    0.06
    ä¾ł
    0.06
    åİļ
    0.06
    имÑĥ
    0.06
    Activations Density 0.205%

    No Known Activations