© 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. 51143
    Prev
    Next
    INDEX
    Explanations

    derivative of

    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
     Beste
    -0.08
    entar
    -0.07
     invi
    -0.07
    endu
    -0.07
    æ§
    -0.07
    embed
    -0.07
     pek
    -0.07
    河山
    -0.06
    bir
    -0.06
    _trial
    -0.06
    POSITIVE LOGITS
     Grie
    0.07
    usser
    0.07
    ä¸ī次
    0.07
    unt
    0.07
    quier
    0.06
    yo
    0.06
    oro
    0.06
     непÑĢ
    0.06
    -env
    0.06
    -sw
    0.06
    Activations Density 0.417%

    No Known Activations