© 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. 18598
    Prev
    Next
    INDEX
    Explanations

    never <verb>

    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
    warz
    -0.08
    ãģıãģªãģĦ
    -0.08
    aren
    -0.08
    LESS
    -0.07
    uret
    -0.07
    veni
    -0.07
    ç§įç§į
    -0.07
    ively
    -0.07
    ÑģÑĥ
    -0.07
    sv
    -0.07
    POSITIVE LOGITS
    theless
    0.14
    -ever
    0.13
     jamás
    0.11
    thing
    0.11
    -ending
    0.09
     EVER
    0.09
    amment
    0.08
    گز
    0.08
     jamais
    0.08
     ever
    0.08
    Activations Density 0.059%

    No Known Activations