© 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. 32988
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers

    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
    nde
    -0.07
     vien
    -0.06
    suspend
    -0.06
    имÑĥ
    -0.06
    óch
    -0.06
    çij
    -0.06
    .nih
    -0.06
    ä½ķä¸į
    -0.06
    opoulos
    -0.06
    åħį
    -0.06
    POSITIVE LOGITS
    ä¸ĭä¸Ģ个
    0.07
    etat
    0.07
    sthet
    0.07
    [next
    0.07
    æ±Łä¸ľ
    0.07
    yat
    0.07
    .interval
    0.06
    好åŃ©åŃIJ
    0.06
    ards
    0.06
    incinnati
    0.06
    Activations Density 0.037%

    No Known Activations