© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 33788
    Prev
    Next
    INDEX
    Explanations

    .StructType, .add, .display, .graphics, .start, .New

    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
    /goto
    -0.09
    ä¹IJä¸ļ
    -0.08
    ibaldi
    -0.08
    ablish
    -0.08
    ÅĤadu
    -0.08
    çĥŃåĬĽ
    -0.08
    acular
    -0.08
    ITAR
    -0.08
    .ReadFile
    -0.08
    BOOLE
    -0.08
    POSITIVE LOGITS
    .
    0.08
    .h
    0.08
    .t
    0.07
    .*
    0.07
    .b
    0.07
    .in
    0.07
    .w
    0.07
    .s
    0.07
    .P
    0.07
    .re
    0.07
    Activations Density 0.589%

    No Known Activations