© 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. 38423
    Prev
    Next
    INDEX
    Explanations

    male, donors, arresting, metaphor

    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
    æľīåı¯èĥ½
    -0.06
     separate
    -0.06
    èĻij
    -0.06
    essin
    -0.06
     scientifically
    -0.06
    æµ·çĩķ
    -0.06
    eda
    -0.06
     Separate
    -0.06
    ä¿Ĺ
    -0.06
    --
    -0.06
    POSITIVE LOGITS
    è¾ĥå¤ļçļĦ
    0.17
    为主çļĦ
    0.17
    为主
    0.16
    -dominated
    0.15
    è¾ĥå¤ļ
    0.14
     predomin
    0.14
    -heavy
    0.14
    å±ħå¤ļ
    0.14
    æĽ´å¤ļçļĦæĺ¯
    0.14
    çĤºä¸»
    0.14
    Activations Density 0.248%

    No Known Activations