© 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. 48031
    Prev
    Next
    INDEX
    Explanations

    sentence start 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
    ר×Ĵ
    -0.06
    CAA
    -0.06
    udios
    -0.06
    æĪijåĴĮå¦Īå¦Ī
    -0.06
    .literal
    -0.06
    èĮĥ
    -0.06
    laf
    -0.06
    cin
    -0.06
    åħļçļĦåįģåħ«å¤§ä»¥æĿ¥
    -0.06
     маÑģÑĤ
    -0.06
    POSITIVE LOGITS
    ¶
    0.08
    rolet
    0.07
     curses
    0.07
    дÑĥа
    0.07
    abd
    0.07
    assy
    0.07
    .pub
    0.07
    моби
    0.07
    TURN
    0.07
    æľįè£ħ设计
    0.07
    Activations Density 0.087%

    No Known Activations