© 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. 11664
    Prev
    Next
    INDEX
    Explanations

    explaining `why`

    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
    allery
    -0.10
    èĨĢ
    -0.09
    èī²åĪĹ
    -0.09
    raries
    -0.09
    ours
    -0.08
    ãģªãĤīãģļ
    -0.08
    INAL
    -0.08
    onto
    -0.08
    æ®ĥ
    -0.08
    plete
    -0.08
    POSITIVE LOGITS
     why
    0.10
    æ¸ħæ¥ļ
    0.08
    为ä»Ģä¹Ī
    0.08
    为ä½ķ
    0.08
    o
    0.08
    ation
    0.07
    why
    0.07
    odie
    0.07
    åħ¶åİŁåĽł
    0.07
    è¿Ļ个éģĵçIJĨ
    0.07
    Activations Density 0.034%

    No Known Activations