© 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. 2432
    Prev
    Next
    INDEX
    Explanations

    C++ code headers

    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
    hift
    -0.08
    åĨ
    -0.08
     volna
    -0.07
    genden
    -0.07
    éĥ½æĺ¯å¾Ī
    -0.07
    isex
    -0.07
    sg
    -0.07
     expres
    -0.06
    lı
    -0.06
     Ank
    -0.06
    POSITIVE LOGITS
    ulam
    0.08
    Scr
    0.07
    追ãģĦ
    0.07
    aly
    0.07
    ák
    0.07
    Dam
    0.06
    ÃŃg
    0.06
    assert
    0.06
    大åIJį
    0.06
    abb
    0.06
    Activations Density 0.006%

    No Known Activations