© 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. 20871
    Prev
    Next
    INDEX
    Explanations

    **can / enables / yourself / design**

    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
    YN
    -0.06
    umb
    -0.06
     coloured
    -0.06
    æį®è¯´
    -0.05
    ought
    -0.05
    (
    -0.05
    à¤ļना
    -0.05
    oit
    -0.05
    åĩºåħ¥
    -0.05
    uffle
    -0.05
    POSITIVE LOGITS
    iston
    0.06
     LATIN
    0.06
    -solid
    0.06
    ignes
    0.06
    ç»ıä¿¡
    0.06
    äss
    0.06
    yti
    0.06
    itere
    0.06
    pagina
    0.06
    æĺ¯éĽĨ
    0.06
    Activations Density 0.012%

    No Known Activations