© 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. 28072
    Prev
    Next
    INDEX
    Explanations

    -less suffixes

    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
    ä¹ħèĢĮ
    -0.08
    ä¹ħä¹ĭ
    -0.07
    館
    -0.07
    æĬĢæľ¯éĹ®é¢ĺ
    -0.07
    misc
    -0.07
    å·²ç»ıè¶ħè¿ĩ
    -0.07
    è·¯å°ıåѦ
    -0.07
    ibase
    -0.07
    ienza
    -0.07
    åIJįçļĦ
    -0.07
    POSITIVE LOGITS
    less
    0.13
    lessness
    0.11
    -less
    0.10
    lessly
    0.10
    ä¸İåIJ¦
    0.09
    åŃĺåľ¨çļĦ
    0.08
    optional
    0.08
    çļĦåŃĺåľ¨
    0.08
     presence
    0.08
    -free
    0.08
    Activations Density 0.239%

    No Known Activations