© 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. 12380
    Prev
    Next
    INDEX
    Explanations

    derivative of

    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
    å°±ä¸Ĭ
    -0.07
    çĿ¹
    -0.07
    ä¸ĬæĿ¥
    -0.06
    죽
    -0.06
     Lai
    -0.06
    ival
    -0.06
    ellini
    -0.06
    vis
    -0.06
    anon
    -0.06
    dock
    -0.06
    POSITIVE LOGITS
    éĩijæ²Ļ
    0.08
    zal
    0.08
    ิà¸Ļ
    0.07
    è¹Ī
    0.07
    assis
    0.07
    åĴĮéĩij
    0.07
    å·®éĶĻ
    0.07
    udge
    0.07
    izr
    0.07
    actics
    0.07
    Activations Density 0.037%

    No Known Activations