© 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. 24729
    Prev
    Next
    INDEX
    Explanations

    special characters or programming symbols

    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
     {}.
    -0.06
    ubi
    -0.06
    å¯ĦãģĽ
    -0.06
    BUF
    -0.06
    ;
    -0.06
     напÑĢа
    -0.06
    .BufferedReader
    -0.06
    ('').
    -0.05
    asi
    -0.05
    åħį
    -0.05
    POSITIVE LOGITS
    ")==
    0.10
    çļĦä¸ĢåĪĩéĥ½
    0.10
    ]]=
    0.10
    çļĦéĹ®é¢ĺæĺ¯
    0.10
    ä½ľçĶ¨æĺ¯
    0.10
    ç«ĭåľºæĹłåħ³
    0.09
    çļĦäººä¹Ł
    0.09
    ?=
    0.09
    ä¸įåIJĮçļĦæĺ¯
    0.09
    ')==
    0.08
    Activations Density 0.021%

    No Known Activations