© 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. 17895
    Prev
    Next
    INDEX
    Explanations

    real or doubt

    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
     Futter
    -0.06
     sỼm
    -0.05
    润
    -0.05
     tendencies
    -0.05
    çIJĨ论
    -0.05
     explaining
    -0.05
    ulik
    -0.05
    çļĦçľ¼åħī
    -0.05
     ÑĢан
    -0.05
     ÐłÐ°Ð½
    -0.05
    POSITIVE LOGITS
    åı¯éĿłçļĦ
    0.06
    åı¯éĿł
    0.05
     personal
    0.05
    对èĩªèº«
    0.05
    åı¯éĿłæĢ§
    0.05
    èĩªå·±éĥ½
    0.05
    ä¿ĿæĬ¤èĩªå·±
    0.05
     Moment
    0.05
    -self
    0.05
     reliable
    0.05
    Activations Density 0.001%

    No Known Activations