© 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. 24480
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    çķ
    -0.07
    å¦Ĵ
    -0.07
    没åĬŀæ³ķ
    -0.06
    -notes
    -0.06
    NOTE
    -0.06
    åĽłæѤèĢĮ
    -0.06
     Shades
    -0.06
    onen
    -0.06
    —for
    -0.05
    åİŁæľīçļĦ
    -0.05
    POSITIVE LOGITS
    agno
    0.09
    å·¦åı³çļĦ
    0.09
    IBUT
    0.08
    临åºĬç»ıéªĮ
    0.08
    irez
    0.08
    беÑĤ
    0.08
    ä¸īä¸ĸ
    0.07
    缸åħ³éĹ®çŃĶ
    0.07
    管çIJĨæ°´å¹³
    0.07
    RIPT
    0.07
    Activations Density 0.044%

    No Known Activations