© 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. 45960
    Prev
    Next
    INDEX
    Explanations

    takes inputs or arguments

    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
    缸åħ³äºĭå®ľ
    -0.07
    break
    -0.07
    à¸ķำ
    -0.07
    roż
    -0.07
    对ä»ĺ
    -0.07
     breakthrough
    -0.07
    åĽ½å®¶å¯¹
    -0.07
    æķ´æĶ¹å·¥ä½ľ
    -0.07
    åħ¶ä»ĸ人
    -0.06
    esak
    -0.06
    POSITIVE LOGITS
     inputs
    0.12
    è¾ĵåħ¥
    0.12
     input
    0.11
    ä¼łåħ¥
    0.09
     Inputs
    0.09
    inputs
    0.09
     arguments
    0.09
    è¾ĵåħ¥çļĦ
    0.09
    input
    0.09
     Input
    0.09
    Activations Density 0.113%

    No Known Activations