© 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. 21125
    Prev
    Next
    INDEX
    Explanations

    detection and identification

    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
    hv
    -0.07
    丸
    -0.06
    ord
    -0.06
    -ish
    -0.06
    yll
    -0.06
    ä¸įåłª
    -0.06
     fucking
    -0.06
    itatea
    -0.06
    ially
    -0.06
    allah
    -0.06
    POSITIVE LOGITS
    ings
    0.15
    åıijçĶŁåľ¨
    0.12
    INGS
    0.11
     erfolgt
    0.10
    tings
    0.10
     erfolgen
    0.09
    athon
    0.09
    éģİçļĦ
    0.09
    ments
    0.09
    ingan
    0.09
    Activations Density 0.769%

    No Known Activations