© 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. 40538
    Prev
    Next
    INDEX
    Explanations

    what

    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
    iett
    -0.08
    ustra
    -0.08
    uhkan
    -0.07
    åIJĦè¡ĮåIJĦ
    -0.07
    èĺĭ
    -0.07
    _$_
    -0.07
    å¦Ĥæŀľåıªæĺ¯
    -0.07
    çŃł
    -0.07
    cies
    -0.07
    eca
    -0.07
    POSITIVE LOGITS
     Ñĥгодно
    0.09
     you
    0.08
     others
    0.08
    soever
    0.08
     previously
    0.07
     else
    0.07
     they
    0.07
    others
    0.07
    /how
    0.07
    éĥ¨å°±
    0.07
    Activations Density 0.316%

    No Known Activations