© 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. 4205
    Prev
    Next
    INDEX
    Explanations

    appeals, sentence, customer, choose

    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
    .addButton
    -0.07
    ä»¥ä¹łè¿ijå¹³
    -0.07
    纳德
    -0.07
    å¦Ĥæŀľä½łæľī
    -0.07
    Defaults
    -0.07
    наÑĤ
    -0.07
    åı«åģļ
    -0.06
    央è§Ĩç½ij
    -0.06
    loff
    -0.06
    ume
    -0.06
    POSITIVE LOGITS
    å¿ĹæĦ¿æľįåĬ¡æ´»åĬ¨
    0.09
    ence
    0.07
    æĥ¨éģŃ
    0.07
    袴
    0.07
    åıĬæĹ¶è¿Ľè¡Į
    0.07
    è¾ĥåݻ年åIJĮæľŁ
    0.07
    表达对
    0.07
    ilien
    0.07
    产ä¸ļ转åŀĭåįĩ级
    0.07
    éĢīæĭ©éĢĤåIJĪèĩªå·±çļĦ
    0.07
    Activations Density 0.050%

    No Known Activations