© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64176
    Prev
    Next
    INDEX
    Explanations

    felony, robbery, conspiracy, crime

    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
    SPAN
    -0.07
     Gros
    -0.07
    ahn
    -0.07
    å¡ģ
    -0.07
    kaar
    -0.07
    賦
    -0.07
    å¸ĺ
    -0.07
    å¢ħ
    -0.07
     disap
    -0.06
     Davies
    -0.06
    POSITIVE LOGITS
    æĺİçŁ¥
    0.10
    æĥħèĬĤ
    0.09
    è°ĭ
    0.09
     accomp
    0.09
    è°ĭåĪĴ
    0.08
    æģ¶åĬ£
    0.08
    çļĦæĥħèĬĤ
    0.08
    为ä»ĸ人
    0.08
    诱
    0.08
    åĽ½å®¶æľºåħ³
    0.08
    Activations Density 0.018%

    No Known Activations