© 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. 17846
    Prev
    Next
    INDEX
    Explanations

    all occurrences 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
    stad
    -0.08
    éļ¾æ±Ĥ
    -0.08
    stw
    -0.08
    _constant
    -0.07
    ä½ķä¸į
    -0.06
    chst
    -0.06
    fan
    -0.06
    λÏī
    -0.06
    upu
    -0.06
    å¦ĤåĽł
    -0.06
    POSITIVE LOGITS
    çĶ·ç¥ŀ
    0.08
    ãĥĶãĥ³ãĤ°
    0.08
     estimação
    0.07
     Blank
    0.07
    trag
    0.07
    udah
    0.07
    æĻī
    0.07
    /components
    0.06
    çī¢åĽºæłijç«ĭ
    0.06
    .tolist
    0.06
    Activations Density 0.012%

    No Known Activations