© 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. 31333
    Prev
    Next
    INDEX
    Explanations

    letter c

    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
    nd
    -0.08
    SSERT
    -0.07
    że
    -0.06
    зал
    -0.06
    elson
    -0.06
    åĹĵåŃIJ
    -0.06
    arat
    -0.06
    emoth
    -0.06
     dama
    -0.06
    ä¸įæĭĶ
    -0.06
    POSITIVE LOGITS
    elsius
    0.09
    ikli
    0.09
    inten
    0.08
    igaret
    0.08
    ayo
    0.08
    ibra
    0.08
    ensored
    0.08
    oven
    0.08
    ramer
    0.08
    ledon
    0.08
    Activations Density 0.001%

    No Known Activations