© 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. 12700
    Prev
    Next
    INDEX
    Explanations

    csv file format

    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
    à´ªàµįà´ªàµĨ
    -0.08
    å²Ĥ
    -0.08
    itzen
    -0.07
     perpet
    -0.07
     forse
    -0.07
     afh
    -0.07
    cind
    -0.07
    åı¯åIJ¦
    -0.07
     наклад
    -0.07
    åĩºåĬ¨
    -0.06
    POSITIVE LOGITS
     preferably
    0.10
    å¿ħé¡»æĺ¯
    0.10
    æľĢ好æĺ¯
    0.09
    èĩ³å°ij
    0.09
    符åIJĪè¦ģæ±Ĥ
    0.08
    è¶Ĭ好
    0.08
     correctly
    0.08
     almeno
    0.08
    ä»»ä½ķå½¢å¼ıçļĦ
    0.08
     beforehand
    0.08
    Activations Density 0.292%

    No Known Activations