© 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. 41849
    Prev
    Next
    INDEX
    Explanations

    risk and areas

    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
    azing
    -0.08
    ibly
    -0.07
    jub
    -0.07
    -eslint
    -0.07
    éĻĪå°ı
    -0.06
    azor
    -0.06
    aze
    -0.06
     Texte
    -0.06
     su
    -0.06
    âĢIJ
    -0.06
    POSITIVE LOGITS
    æĥł
    0.08
    è¿ľåľ¨
    0.08
    ÑĤил
    0.08
    uir
    0.07
    _PROGRAM
    0.07
    åħ°å¾·
    0.07
     avs
    0.07
    æ¯ĶåĪ«äºº
    0.07
    loff
    0.07
    UDI
    0.07
    Activations Density 1.504%

    No Known Activations