© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63123
    Prev
    Next
    INDEX
    Explanations

    inf or factor

    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
    ness
    -0.13
    Ø©
    -0.12
    缸è¾ħ缸æĪIJ
    -0.11
    ation
    -0.10
    åĬłæĭ¿å¤§
    -0.10
    es
    -0.09
    ed
    -0.09
    æĸ°åĬłåĿ¡
    -0.09
    ãģ¾ãģ¾
    -0.09
    æ¯Ľæ³½ä¸ľ
    -0.08
    POSITIVE LOGITS
    ãģĵãĤĮãģ§
    0.09
    umo
    0.09
    ÑĢон
    0.08
    isikan
    0.08
    ãģ¿ãģ«
    0.08
    voi
    0.08
    ambu
    0.08
    ĸ
    0.08
    ITIES
    0.08
    zelfde
    0.08
    Activations Density 0.001%

    No Known Activations