© 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. 19834
    Prev
    Next
    INDEX
    Explanations

    RSVP

    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
    èĩªå·±æľī
    -0.06
     tindak
    -0.06
     chuá»Ļng
    -0.06
    andu
    -0.06
    ’ve
    -0.06
    ä¸ŃåĽ½åĽ½å®¶
    -0.06
    ä¸ĭåIJĮ
    -0.05
     citas
    -0.05
    ä¸ŃåĽ½ç¤¾ä¼ļ
    -0.05
    USED
    -0.05
    POSITIVE LOGITS
     sac
    0.06
     olaraq
    0.05
    åĬ£
    0.05
    ìĹŃ
    0.05
    kits
    0.05
    erschein
    0.05
    é«ĺçŃī
    0.05
     attempt
    0.05
    emb
    0.05
    embl
    0.05
    Activations Density 0.001%

    No Known Activations