© 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. 10179
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No. preceding 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
    ensee
    -0.07
    iat
    -0.07
    веÑĨ
    -0.07
    лиÑĩ
    -0.06
    å°ıå¹³
    -0.06
    è°ħ
    -0.06
    enor
    -0.06
    ator
    -0.06
    è¯Ħ级
    -0.06
    éĵ¶å±±
    -0.06
    POSITIVE LOGITS
    æľĽ
    0.07
    å·®ä¸į
    0.07
    μή
    0.07
    xada
    0.07
    å¿ĺ
    0.07
     suppress
    0.07
    åIJĮåѦéĥ½
    0.07
    æľĪ份å¼Ģå§ĭ
    0.07
    ,cp
    0.07
     suppressing
    0.07
    Activations Density 0.010%

    No Known Activations