© 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. 26097
    Prev
    Next
    INDEX
    Explanations

    quotation marks and delimiters

    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¿ħæľī
    -0.08
    obot
    -0.07
    ிர
    -0.06
    å¦Ĥæ½®
    -0.06
    urb
    -0.06
     Honor
    -0.06
    è¡Ķ
    -0.06
    azi
    -0.06
    ower
    -0.06
     kn
    -0.06
    POSITIVE LOGITS
    åĬłæĭ¿å¤§
    0.08
    apis
    0.08
    <|box_end|>
    0.07
    éĢ¢
    0.07
    ¾¸
    0.07
    lje
    0.07
    manos
    0.07
     pomi
    0.07
     sade
    0.07
    /apis
    0.07
    Activations Density 0.055%

    No Known Activations