© 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. 51625
    Prev
    Next
    INDEX
    Explanations

    example, laws

    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
    ags
    -0.07
    åľ¨åIJĦ个
    -0.07
    -core
    -0.06
    ondo
    -0.06
    就差
    -0.06
    ä½łåĪ°åºķ
    -0.06
    被
    -0.06
    laut
    -0.06
    ond
    -0.06
    å°Ĩè¿ij
    -0.06
    POSITIVE LOGITS
     ìĺĪ를
    0.11
     például
    0.11
    ä¾ĭå¦Ĥ
    0.11
     bijvoorbeeld
    0.11
    ä»»éĢī
    0.11
     напÑĢимеÑĢ
    0.11
    ä¸Ģä¾ĭ
    0.10
     napÅĻÃŃklad
    0.10
    /example
    0.10
    æ¯Ķå¦Ĥåľ¨
    0.10
    Activations Density 0.011%

    No Known Activations