© 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. 12748
    Prev
    Next
    INDEX
    Explanations

    inverse of

    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
    ве
    -0.07
    裹
    -0.07
    ysten
    -0.06
    ÑĩеÑĢед
    -0.06
    оÑĢи
    -0.06
    çĶŁ
    -0.06
    è¿Ļæĺ¯å¯¹
    -0.06
    ãĤ¢ãĥ©
    -0.06
    å¦Īå¦Ī说
    -0.06
    æŃ¤ä¸º
    -0.06
    POSITIVE LOGITS
    æĽ
    0.08
    tiger
    0.08
    ึà¸ĩ
    0.08
    æ¸Ī
    0.07
    essen
    0.07
    _Var
    0.07
    áb
    0.07
     вп
    0.07
    imitive
    0.07
    èĬ¹
    0.07
    Activations Density 0.001%

    No Known Activations