© 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. 21152
    Prev
    Next
    INDEX
    Explanations

    facts or details about

    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
    athing
    -0.08
    omon
    -0.08
    æľ¬è¯¾ç¨ĭ
    -0.07
    areth
    -0.07
    ultz
    -0.07
    è··
    -0.07
    elj
    -0.07
    å¾Ĵ
    -0.07
    å¤Ħæĸ¹
    -0.07
    apt
    -0.07
    POSITIVE LOGITS
    å¤ļç¯ĩ
    0.08
    ä¸Ģç¯ĩ
    0.07
    à¹Ģรียà¸ĩ
    0.07
    ä¼ĺç§ĢçļĦ
    0.07
    PP
    0.07
    æĸĩä¸ŃçļĦ
    0.07
    .pp
    0.07
    ta
    0.07
    mark
    0.07
    çĶĦéĢī
    0.07
    Activations Density 0.003%

    No Known Activations