© 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. 32840
    Prev
    Next
    INDEX
    Explanations

    suffix "-less"

    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
    atot
    -0.08
    isers
    -0.07
    æ¯ıä¸Ģ项
    -0.07
    uan
    -0.07
    à¹Ģà¸ŀลิà¸ĩ
    -0.07
    ÙİØ«
    -0.07
    è´¹æŶ
    -0.07
    ä¸ĢèĪ¬éĥ½ä¼ļ
    -0.07
    åĽĽåįĥ
    -0.07
    ENSE
    -0.07
    POSITIVE LOGITS
    lessly
    0.08
    adge
    0.08
    lessness
    0.08
     اÙĦÙĪØŃ
    0.08
    ä»Ģä¹ĪåİŁåĽł
    0.07
    äºĽ
    0.07
    less
    0.07
    åIJĹ
    0.07
    æ»
    0.07
    à¹Ģลà¹ĩà¸ģà¸Ļà¹īà¸Ńย
    0.07
    Activations Density 0.034%

    No Known Activations