© 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. 57288
    Prev
    Next
    INDEX
    Explanations

    Leslie speaker

    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
    istration
    -0.07
    ils
    -0.07
    erosis
    -0.06
    iates
    -0.06
    riqu
    -0.06
    θοÏĤ
    -0.06
    reja
    -0.06
    Ħ
    -0.06
    ortal
    -0.06
    ansi
    -0.06
    POSITIVE LOGITS
    zelfde
    0.10
    jenigen
    0.10
    ê¹IJ
    0.09
    дÑĢо
    0.08
    çĦ¶å¤§
    0.08
    य
    0.08
    ãģ¨ãģĦãģ£ãģ¦
    0.08
    à¹Ī
    0.08
    λάÏĩιÏĥ
    0.08
    inition
    0.08
    Activations Density 2.370%

    No Known Activations