© 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. 20874
    Prev
    Next
    INDEX
    Explanations

    question words and punctuation

    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
    åı¯èĥ½æĺ¯
    -0.06
    å¾Īéļ¾
    -0.06
    çİ©çİ©
    -0.06
    大æ¦Ĥæĺ¯
    -0.06
    æŁ¥
    -0.06
    ä»ĭäºİ
    -0.05
    åı¯èĥ½éľĢè¦ģ
    -0.05
    æ¶Ī
    -0.05
    æµĭ
    -0.05
    å¦Ĥæŀľæĺ¯
    -0.05
    POSITIVE LOGITS
    ilen
    0.07
    iten
    0.06
    å¦ĩ产
    0.06
    ism
    0.06
    ibox
    0.06
    åĽ²
    0.06
    åİ»åĵª
    0.06
    ija
    0.06
    itra
    0.05
    åĵī
    0.05
    Activations Density 0.005%

    No Known Activations