© 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. 61092
    Prev
    Next
    INDEX
    Explanations

    TODO or FIXME comments

    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
    adera
    -0.09
    大è§Ĥ
    -0.08
    -vars
    -0.08
    abora
    -0.08
    luv
    -0.08
    缴æĴŃ带货
    -0.08
    ä¸Ń大
    -0.08
    çŃł
    -0.08
    installer
    -0.08
    ulumi
    -0.08
    POSITIVE LOGITS
     FIXME
    0.08
    FIXME
    0.07
     TODO
    0.07
     presently
    0.07
    æľīå¾ħ
    0.07
     currently
    0.07
    TODO
    0.07
    currently
    0.06
    éĽªçĻ½çļĦ
    0.06
    è¡Įä¹ĭ
    0.06
    Activations Density 0.064%

    No Known Activations