© 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. 28143
    Prev
    Next
    INDEX
    Explanations

    job/candidate placement

    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
    Ops
    -0.08
    Cli
    -0.08
    <small
    -0.07
    ä¹Ŀ寨
    -0.07
    å¼Ħ
    -0.07
    å¾ĭ
    -0.07
    ×ķ×ĸ
    -0.07
    ocha
    -0.07
     NSError
    -0.07
    -op
    -0.07
    POSITIVE LOGITS
    ainer
    0.07
    ander
    0.07
    ianto
    0.07
    è´µ
    0.07
    å¦Ĥæŀľæľī
    0.07
     presumably
    0.07
    èľĹçīĽ
    0.07
    whatever
    0.07
    ç¿ł
    0.07
    éĶ¡
    0.07
    Activations Density 0.105%

    No Known Activations