© 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. 23812
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers

    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
    her
    -0.07
    qq
    -0.07
    ddd
    -0.06
    åı°
    -0.06
    ø
    -0.06
    ia
    -0.06
    abl
    -0.06
    éĻĪçļ®
    -0.06
    åı°åīį
    -0.06
    å¦ĤçĥŁ
    -0.06
    POSITIVE LOGITS
    ä½ķä¸į
    0.08
    åıĸå¾ĹçļĦæĪIJ绩
    0.08
    Å¡n
    0.08
    ä¸įåı¯æĢĿè®®
    0.08
    ç½Ĺæĭī
    0.07
    éĿ¢ç§¯è¾¾
    0.07
    kes
    0.07
    èijĨ
    0.07
    计åĪĴçļĦ
    0.07
    åĬłæĭ¿å¤§
    0.07
    Activations Density 0.020%

    No Known Activations