© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20102
    Prev
    Next
    INDEX
    Explanations

    as i

    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
    arine
    -0.06
    å¼Ģå§ĭæŶ
    -0.05
    å¼Ģå§ĭçļĦ
    -0.05
    ç½Ĺæ±ī
    -0.05
    æĸ¹
    -0.05
     jär
    -0.05
    åIJİç¼Ģ
    -0.05
    è§ģéĿ¢
    -0.05
    ipient
    -0.05
     gre
    -0.04
    POSITIVE LOGITS
    reichen
    0.07
    转ä¼ļ
    0.07
    ä½£
    0.06
    ulich
    0.06
    ulat
    0.06
    转移
    0.06
    è´¥
    0.06
    次åĽŀ
    0.06
    Æ¡m
    0.06
    yg
    0.06
    Activations Density 0.005%

    No Known Activations