© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16917
    Prev
    Next
    INDEX
    Explanations

    expresses negation or necessity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĢļ
    -0.06
    eks
    -0.06
    ä¸ĢåĪĩ
    -0.06
    å®ĥä»¬åľ¨
    -0.06
    ÑĤок
    -0.05
    elas
    -0.05
    weich
    -0.05
    è¶ĭåĬ¿
    -0.05
    æľīä»»ä½ķ
    -0.05
     maintain
    -0.05
    POSITIVE LOGITS
    UCA
    0.06
    æĪIJæĮĩ
    0.06
    comings
    0.05
     Kapit
    0.05
    ves
    0.05
    akter
    0.05
    ×Ļרת
    0.05
     ØŃÙĤÙĬÙĤÙĬØ©
    0.05
     terminals
    0.05
     raffin
    0.05
    Activations Density 0.031%

    No Known Activations