© 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. 51315
    Prev
    Next
    INDEX
    Explanations

    recording and writing information

    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
    ç½ijç«Ļ导èĪª
    -0.08
    ä¾ĥ
    -0.07
    ç«Ļåľ¨äºĨ
    -0.07
    caler
    -0.07
    uda
    -0.07
    _plural
    -0.07
    PerPixel
    -0.07
    resh
    -0.07
    éĺ²æ¯Ĵ
    -0.07
    veal
    -0.06
    POSITIVE LOGITS
    è®°å½ķ
    0.23
     record
    0.20
    è®°å½ķäºĨ
    0.19
     records
    0.19
    è®°å½ķçļĦ
    0.19
    è®°å½ķåĴĮ
    0.18
     recording
    0.18
    è®°å½ķä¸ĭ
    0.18
    record
    0.18
    è¨ĺéĮĦ
    0.18
    Activations Density 0.345%

    No Known Activations