© 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. 50483
    Prev
    Next
    INDEX
    Explanations

    data structures and code

    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
    akor
    -0.07
    <decltype
    -0.07
    å°§
    -0.07
    å½ĵåħ¶
    -0.07
    uesa
    -0.07
     biss
    -0.07
    å½ĵåľº
    -0.07
    _bins
    -0.06
    /js
    -0.06
    è½»
    -0.06
    POSITIVE LOGITS
    _layers
    0.07
    etÃŃ
    0.07
    åľĪ
    0.07
    æĶĺ
    0.07
    amespace
    0.07
    æĽ´æ·±
    0.06
    å»
    0.06
     Inner
    0.06
    _KP
    0.06
    æ±°
    0.06
    Activations Density 0.092%

    No Known Activations