© 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. 20504
    Prev
    Next
    INDEX
    Explanations

    section titles or formatting

    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
     Yankees
    -0.07
     Âł
    -0.07
     Âł Âł
    -0.06
    èħĨ
    -0.06
    uson
    -0.06
    æī¿æĭħä¸ĢåĪĩ
    -0.06
     Âł Âł Âł Âł
    -0.06
    ctrine
    -0.06
    arser
    -0.06
     Tew
    -0.06
    POSITIVE LOGITS
    æ¹¾
    0.08
    çī¹åĪ«å£°æĺİ
    0.07
    mutable
    0.07
    estig
    0.07
    tij
    0.07
    haar
    0.07
    _CHANGED
    0.07
    à¹Ģลยà¸Ĺีà¹Ģà¸Ķียว
    0.07
    hip
    0.06
    redits
    0.06
    Activations Density 0.104%

    No Known Activations