© 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. 60663
    Prev
    Next
    INDEX
    Explanations

    company and group names

    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
    ancing
    -0.07
    åħ¬åı¸èij£äºĭéķ¿
    -0.07
    icions
    -0.06
    æĪijè¿ĺæĺ¯
    -0.06
    áp
    -0.06
    大åįĥ
    -0.06
    ениÑı
    -0.06
     pies
    -0.06
     i
    -0.06
    &id
    -0.06
    POSITIVE LOGITS
    untlet
    0.08
    iless
    0.08
    å½ĵåīįä½įç½®
    0.08
    unki
    0.08
    lek
    0.08
    iligen
    0.08
    osphere
    0.07
    ÃŃž
    0.07
    lla
    0.07
    schnitt
    0.07
    Activations Density 2.203%

    No Known Activations