© 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. 43429
    Prev
    Next
    INDEX
    Explanations

    tilt and bias

    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
     Kolej
    -0.08
    ÑĢаÑĤно
    -0.07
    UDI
    -0.07
    aya
    -0.07
    stants
    -0.07
    kuit
    -0.07
    κει
    -0.07
    #__
    -0.07
    Descriptor
    -0.06
    ingan
    -0.06
    POSITIVE LOGITS
    ä¸į为
    0.11
     nonzero
    0.10
     ненÑĥ
    0.09
     bias
    0.09
    Bias
    0.09
    bias
    0.09
    åģıåIJij
    0.09
    åģıå¿ĥ
    0.08
     Bias
    0.08
     пÑĢедна
    0.08
    Activations Density 0.070%

    No Known Activations