© 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. 38165
    Prev
    Next
    INDEX
    Explanations

    random occurrence or specific outcomes

    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
    æĤĦæĤĦ
    -0.09
    ä¸įåĪĨ
    -0.09
     tÃŃ
    -0.08
    ç®Ģåįķåľ°
    -0.08
    æĤĦæĹłå£°
    -0.08
    毫æĹł
    -0.07
    æĹłè§Ĩ
    -0.07
    èche
    -0.07
    æķ´å¤©
    -0.07
    åįķçĭ¬çļĦ
    -0.07
    POSITIVE LOGITS
     yet
    0.09
    ä½Ĩèĩ³å°ij
    0.08
     but
    0.08
    yet
    0.07
    -ish
    0.07
     doch
    0.07
    ãģĭãĤĤãģĹãĤĮãģ¾ãģĽãĤĵãģĮ
    0.07
    æ¯Ķè¾ĥå¤ļ
    0.07
    bol
    0.06
    ä½Ĩæľī
    0.06
    Activations Density 0.288%

    No Known Activations