© 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. 40258
    Prev
    Next
    INDEX
    Explanations

    perform/action

    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
    seg
    -0.09
    ideo
    -0.07
    ÑģÑĤÑĥ
    -0.07
    è¿Ļ个大
    -0.07
    zerw
    -0.07
    cala
    -0.07
    kev
    -0.06
    omatic
    -0.06
    uild
    -0.06
    igham
    -0.06
    POSITIVE LOGITS
    åĬłæĭ¿å¤§
    0.10
    enz
    0.07
    çĶļèĩ³è¿ĺ
    0.07
    äºĮæĺ¯è¦ģ
    0.06
    errat
    0.06
    ãĢįãĢģ
    0.06
    åıij表è¯Ħ论
    0.06
    æĪĸ以
    0.06
    {},
    0.06
    rÃł
    0.06
    Activations Density 0.011%

    No Known Activations