© 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. 42955
    Prev
    Next
    INDEX
    Explanations

    special characters or punctuation

    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
    .tpl
    -0.08
    .herokuapp
    -0.08
    icht
    -0.07
    ä¸į误
    -0.07
    éļ¾æ±Ĥ
    -0.07
    acobian
    -0.07
    çľ¼åħī
    -0.07
    iverse
    -0.07
    .dat
    -0.07
    abilidade
    -0.07
    POSITIVE LOGITS
    对äºİä¸Ģ个
    0.07
    éĽ·é¸£
    0.07
    ecker
    0.06
    ább
    0.06
    è¡·å¿ĥçļĦ
    0.06
    omi
    0.06
    ÑĢÑĭн
    0.06
    cione
    0.06
    otte
    0.06
    èĩªæĪijçļĦ
    0.06
    Activations Density 0.392%

    No Known Activations