© 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. 3849
    Prev
    Next
    INDEX
    Explanations

    that identifies

    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
    емо
    -0.07
    使å®ĥ
    -0.07
    以åıĬä¸İ
    -0.07
    zá
    -0.06
    使åħ¶
    -0.06
    ais
    -0.06
    cci
    -0.06
    ế
    -0.06
    aal
    -0.06
    对åħ¶
    -0.06
    POSITIVE LOGITS
    æĬĬ
    0.08
    çļĦçī¹çĤ¹æĺ¯
    0.08
    ä¸ĵéŨ
    0.08
    è¿ĶåĽŀ缮å½ķ
    0.08
    åıªæıIJä¾Ľ
    0.08
    çī¹çĤ¹æĺ¯
    0.07
    æ¯Ķè¾ĥå¤įæĿĤ
    0.07
    arczy
    0.07
    allow
    0.07
    ä¸ĵ为
    0.07
    Activations Density 0.281%

    No Known Activations