© 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. 8342
    Prev
    Next
    INDEX
    Explanations

    incremented, counting, ordinal, Askey–Wilson

    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
    yata
    -0.08
    çĺŁ
    -0.08
    ssen
    -0.07
    çons
    -0.07
    ijIJ
    -0.07
    ault
    -0.07
     dise
    -0.07
    kis
    -0.07
    Äįov
    -0.07
    quete
    -0.07
    POSITIVE LOGITS
    azah
    0.08
    áŀ¶áŀĶáŁĭ
    0.07
     incremented
    0.07
     Kita
    0.07
     counting
    0.07
     anz
    0.07
     Rasa
    0.07
    .ordinal
    0.06
     BAM
    0.06
    BAS
    0.06
    Activations Density 0.001%

    No Known Activations