© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2706
    Prev
    Next
    INDEX
    Explanations

    questions about statements

    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
    uhl
    -0.08
    anen
    -0.07
     defe
    -0.07
    UBLE
    -0.07
    åıįä¹īè¯į
    -0.07
     ucwords
    -0.07
    tes
    -0.06
    atched
    -0.06
    หาà¸Ķ
    -0.06
    ÑĢÑıÑĤ
    -0.06
    POSITIVE LOGITS
    âij
    0.08
     together
    0.08
    çļĦä¸Ģç³»åĪĹ
    0.08
    çļĦä¸Ģç»Ħ
    0.08
    .serial
    0.07
    æľ¬é¢ĺçŃĶæ¡Ī
    0.07
     #@
    0.07
    imson
    0.07
    acer
    0.07
    åĵªäºĽ
    0.07
    Activations Density 0.004%

    No Known Activations