© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23031
    Prev
    Next
    INDEX
    Explanations

    evening or parcel

    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
    ffi
    -0.07
    stens
    -0.07
     Ñĥгодно
    -0.07
    ificate
    -0.07
    бок
    -0.07
    .linkedin
    -0.07
    udeau
    -0.07
    obat
    -0.07
    zyw
    -0.07
    igr
    -0.07
    POSITIVE LOGITS
    ä¸ī个åŃĹ
    0.10
    涯
    0.08
    åħ®
    0.08
    ä¸īåŃĹ
    0.08
    ä»ĭçŁ³
    0.08
    çķĶ
    0.07
    å¼ıçļĦ
    0.07
    æ±Łå±±
    0.07
    åįģ足
    0.06
    ä¼¼çļĦ
    0.06
    Activations Density 0.034%

    No Known Activations