© 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. 38598
    Prev
    Next
    INDEX
    Explanations

    purpose and meaning

    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
    vents
    -0.09
    unce
    -0.08
    elize
    -0.08
    leven
    -0.08
    enco
    -0.08
    aime
    -0.08
    elere
    -0.08
    andr
    -0.08
     onver
    -0.08
    ditor
    -0.08
    POSITIVE LOGITS
    ation
    0.07
    adt
    0.06
    ä½Ĩä¸įéĻIJäºİ
    0.06
     wording
    0.06
    ment
    0.06
    ä¹Łå°±æĺ¯è¯´
    0.06
     cu
    0.06
    ings
    0.06
    ry
    0.06
     needed
    0.05
    Activations Density 0.001%

    No Known Activations