© 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. 39849
    Prev
    Next
    INDEX
    Explanations

    story followed by 'For' or 'in'

    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
    ed
    -0.08
    ãĥªãĤ¨
    -0.07
    رÙĥ
    -0.07
    öch
    -0.07
     gil
    -0.07
     carri
    -0.07
    ieben
    -0.07
    ´
    -0.07
    稳å®ļ
    -0.06
    åĨ¥
    -0.06
    POSITIVE LOGITS
    enni
    0.10
    æĸ°åĬłåĿ¡
    0.08
    éĢļè¿ĩ以ä¸Ĭ
    0.08
    缸è¾ħ缸æĪIJ
    0.08
    峪
    0.08
     druž
    0.08
    .LA
    0.07
    awah
    0.07
    dem
    0.07
    æĢ»ç»ĵå¦Ĥä¸ĭ
    0.07
    Activations Density 0.001%

    No Known Activations