© 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. 26708
    Prev
    Next
    INDEX
    Explanations

    c followed by punctuation

    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
    ад
    -0.08
    人æĦı
    -0.07
    oczy
    -0.07
    ses
    -0.07
    éģIJ
    -0.07
    anter
    -0.06
    à¸Ķย
    -0.06
    adne
    -0.06
    ëĤ©
    -0.06
    ÑĥÑĤа
    -0.06
    POSITIVE LOGITS
     (!((
    0.08
    åı¦æľī
    0.07
    chu
    0.07
    champ
    0.07
    \.
    0.07
    каде
    0.07
    jp
    0.07
     (*(
    0.07
    cha
    0.07
    LBL
    0.06
    Activations Density 0.003%

    No Known Activations