© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22301
    Prev
    Next
    INDEX
    Explanations

    human being

    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
    èµ°å¼±
    -0.07
    ä¸įæĮ¯
    -0.06
    ift
    -0.06
    ToRemove
    -0.06
    usters
    -0.06
    onal
    -0.06
    è¡ĢçĹĩ
    -0.05
    ort
    -0.05
    onial
    -0.05
     меÑĢÑĤ
    -0.05
    POSITIVE LOGITS
    ince
    0.06
    AGER
    0.05
    eller
    0.05
    æłĩåĩĨè¦ģæ±Ĥ
    0.05
    è¨Ī
    0.05
    åłĤ
    0.05
    ÙĪاج
    0.05
    umi
    0.05
    åºŀ
    0.05
     Cent
    0.05
    Activations Density 0.021%

    No Known Activations