© 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. 18613
    Prev
    Next
    INDEX
    Explanations

    bold text followed by non-Latin characters

    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
    estroy
    -0.08
    /from
    -0.08
    vert
    -0.07
    ziali
    -0.07
    ruik
    -0.07
    vedere
    -0.07
    Å¡Äį
    -0.07
    returnValue
    -0.07
    izer
    -0.07
    erd
    -0.07
    POSITIVE LOGITS
    缸è¾ħ缸æĪIJ
    0.20
    es
    0.15
    çļĦ
    0.13
    æĸ°åĬłåĿ¡
    0.13
    ÛĮ
    0.13
    æ¯Ľæ³½ä¸ľ
    0.12
    åĬłæĭ¿å¤§
    0.12
    äºĭåįĬåĬŁåĢį
    0.12
    åĭĩå¾Ģ缴åīį
    0.11
    ÏĤ
    0.11
    Activations Density 0.010%

    No Known Activations