© 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. 58712
    Prev
    Next
    INDEX
    Explanations

    Miacora and Bulia genera

    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
    yles
    -0.08
    itage
    -0.08
    åıªæĺ¯åľ¨
    -0.08
    ourney
    -0.07
    виÑĩ
    -0.07
     Lite
    -0.07
    yle
    -0.07
    opard
    -0.06
    aty
    -0.06
    æŁIJäºĽ
    -0.06
    POSITIVE LOGITS
    fax
    0.07
    amer
    0.07
    æv
    0.07
    пÑĥлÑĮ
    0.07
    mma
    0.07
    remen
    0.07
    pati
    0.07
    lah
    0.07
    ãĤģãĤĵ
    0.07
    mur
    0.07
    Activations Density 0.001%

    No Known Activations