© 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. 64919
    Prev
    Next
    INDEX
    Explanations

    We followed by verb

    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
    è¿IJæ°Ķ
    -0.06
    ç¨ĭ度ä¸Ĭ
    -0.06
    Screens
    -0.06
    .
    -0.06
    ificates
    -0.06
    tv
    -0.06
    ae
    -0.06
    inken
    -0.06
    åħ³ç³»
    -0.06
     Wester
    -0.05
    POSITIVE LOGITS
    èĩªå·±åģļ
    0.09
    intptr
    0.08
    èĩªå·±çĭ¬çī¹çļĦ
    0.08
    flate
    0.08
    ÏĩÏİ
    0.08
    awn
    0.07
    еÑĤка
    0.07
    Ñģил
    0.07
    à¦ķà§įত
    0.07
    stead
    0.07
    Activations Density 0.002%

    No Known Activations