© 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. 58209
    Prev
    Next
    INDEX
    Explanations

    negative values and boundaries

    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
    èıł
    -0.08
    uju
    -0.07
    ìĭ¸
    -0.07
    æ¯ħ
    -0.07
    voi
    -0.07
    ìĿ´ìĬ¤
    -0.07
    usal
    -0.07
    angkan
    -0.07
    è·»
    -0.07
    è¾ĥæħ¢
    -0.07
    POSITIVE LOGITS
     impossible
    0.08
    æĺ¾çĦ¶æĺ¯
    0.08
    ä¸įåIJĪçIJĨ
    0.08
    æĺ¯ä¸įåı¯èĥ½çļĦ
    0.07
     Impossible
    0.07
     unrealistic
    0.07
    æĬµæ¶Ī
    0.07
    ack
    0.07
    æĺ¾çĦ¶
    0.07
    ",-
    0.07
    Activations Density 0.005%

    No Known Activations