© 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. 8563
    Prev
    Next
    INDEX
    Explanations

    split string or list

    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
    spflicht
    -0.09
    ities
    -0.09
    æĶ¾çŁ¢
    -0.09
    oodoo
    -0.09
    evol
    -0.09
    clus
    -0.09
    IZED
    -0.08
    beren
    -0.08
     xuyên
    -0.08
    ehand
    -0.08
    POSITIVE LOGITS
    ting
    0.11
    wise
    0.08
    ب
    0.08
    (',')[
    0.08
    agem
    0.08
    ter
    0.08
    ('.')[
    0.08
    aneous
    0.08
    u
    0.07
    /div
    0.07
    Activations Density 0.014%

    No Known Activations