© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11773
    Prev
    Next
    INDEX
    Explanations

    structure shared download

    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
    ccion
    -0.07
    çĽ¸ä¼´
    -0.07
    çݯçIJĥ
    -0.07
    icha
    -0.06
    egio
    -0.06
    oloc
    -0.06
    ÑģÑĤоÑı
    -0.06
    vist
    -0.06
    irus
    -0.06
    ãģĽãĤĵ
    -0.06
    POSITIVE LOGITS
    atem
    0.09
     Sink
    0.09
    pong
    0.08
    velle
    0.08
    èĥ¤
    0.07
    essim
    0.07
    aven
    0.07
    ak
    0.07
     synerg
    0.07
    Sink
    0.07
    Activations Density 0.001%

    No Known Activations