© 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. 27174
    Prev
    Next
    INDEX
    Explanations

    seq owner, Guides Licensing, Kafka continued

    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
    好货
    -0.07
    crud
    -0.07
    inand
    -0.07
     pÃŃ
    -0.06
    esser
    -0.06
    wier
    -0.06
    Ñįм
    -0.06
    _MISC
    -0.06
    essão
    -0.06
    ------+------+
    -0.06
    POSITIVE LOGITS
    aza
    0.07
    太åı¤
    0.07
    jours
    0.07
    两头
    0.07
    .business
    0.07
    ByUrl
    0.07
    åħį
    0.07
    ãĥįãĥ«
    0.06
    彩äºij
    0.06
    æĪijå¦Ī
    0.06
    Activations Density 0.725%

    No Known Activations