© 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. 50978
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation or closing brackets

    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
    è¿Ļç§įè¡Į为
    -0.06
    -0.06
    åIJĥä¸ĢäºĽ
    -0.06
    ieri
    -0.06
    å®ĥå°±æĺ¯
    -0.05
    opp
    -0.05
    ä¸ĭä¸Ģ级
    -0.05
    éĺ´åĩī
    -0.05
    seau
    -0.05
    wis
    -0.05
    POSITIVE LOGITS
    å¤©æ±ł
    0.08
    ิà¸Ķ
    0.08
    ίοÏħ
    0.08
    cati
    0.08
    æĪ·æĻĵ
    0.08
    说å¾Ĺ
    0.08
    vertiser
    0.07
    corre
    0.07
    /OR
    0.07
    опаÑģ
    0.07
    Activations Density 0.008%

    No Known Activations