© 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. 1155
    Prev
    Next
    INDEX
    Explanations

    json/code structures

    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
    æµİ
    -0.07
     Broad
    -0.07
    uld
    -0.07
     mok
    -0.06
    Dash
    -0.06
    edd
    -0.06
     Vis
    -0.06
    iter
    -0.06
    æĤ
    -0.06
    _Generic
    -0.06
    POSITIVE LOGITS
    æĹłéľĢ
    0.13
    ä¸įéľĢè¦ģ
    0.12
    æĹłé¡»
    0.11
    çĦ¡éľĢ
    0.10
    ä¸įåŃĺåľ¨
    0.09
    ä¸įéľĢ
    0.09
    没æľīéĹ®é¢ĺ
    0.08
    stroy
    0.08
    å°±ä¸įçĶ¨
    0.08
    .generated
    0.08
    Activations Density 0.145%

    No Known Activations