© 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. 21853
    Prev
    Next
    INDEX
    Explanations

    more developed

    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
    awat
    -0.06
    ä¸ĵä¸ļåĴĮ
    -0.06
    —in
    -0.06
    裸
    -0.06
    environnement
    -0.06
    æľ¬æ¡Ī
    -0.05
    ä¸Ģçݯ
    -0.05
    辦
    -0.05
    -options
    -0.05
    koli
    -0.05
    POSITIVE LOGITS
    å¦Ĥæ½®
    0.06
    æĦıåĽ¾
    0.06
    ä¸ĭèIJ½
    0.06
    rens
    0.06
    наÑĩ
    0.06
     respective
    0.05
    ç»Ĩèĩ´
    0.05
    itime
    0.05
    ament
    0.05
    ensible
    0.05
    Activations Density 0.001%

    No Known Activations