© 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. 1080
    Prev
    Next
    INDEX
    Explanations

    senators condemn

    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
     scratches
    -0.08
    entin
    -0.07
    ä¼İ
    -0.07
    veau
    -0.07
    elight
    -0.07
    æĹłå¤Ħ
    -0.07
    .Style
    -0.07
     лома
    -0.07
    éģ¿è®©
    -0.07
    ué
    -0.07
    POSITIVE LOGITS
     probabilities
    0.10
     probability
    0.10
    Probability
    0.09
    æ¦Ĥçİĩ
    0.09
    probability
    0.09
     Probability
    0.08
    lev
    0.08
    enumerator
    0.08
    _probability
    0.08
     statist
    0.08
    Activations Density 0.005%

    No Known Activations