© 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. 13788
    Prev
    Next
    INDEX
    Explanations

    matrix or array operations

    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
    £
    -0.08
    ngle
    -0.08
    ¤
    -0.08
    çĥ§
    -0.07
    RenderingContext
    -0.07
    eson
    -0.07
    agas
    -0.07
    æIJŃ
    -0.07
    SID
    -0.07
    pty
    -0.07
    POSITIVE LOGITS
    å¾Ĺåħ¶
    0.08
    åīį两
    0.08
    coords
    0.07
    rint
    0.07
    TOT
    0.07
    åIJĦ项è§Ħç«łåĪ¶åº¦
    0.07
    umat
    0.07
    با
    0.07
    -compatible
    0.06
    kout
    0.06
    Activations Density 0.009%

    No Known Activations