© 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. 51230
    Prev
    Next
    INDEX
    Explanations

    .Serialization; Monaco; .Diagnostics; .app

    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
    opt
    -0.07
    Ex
    -0.07
    åıĪåľ¨
    -0.07
    oad
    -0.07
     opt
    -0.07
    _opt
    -0.06
    ex
    -0.06
    ido
    -0.06
    Opt
    -0.06
     Opt
    -0.06
    POSITIVE LOGITS
    æľĢåħ¨
    0.08
    зо
    0.08
    বà§ĩ
    0.07
     Limo
    0.07
    è½®æľº
    0.07
    åĽŀæī§
    0.07
    jaht
    0.07
    zusetzen
    0.07
    驱åĬ¨åĻ¨
    0.07
    toi
    0.07
    Activations Density 0.499%

    No Known Activations