© 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. 17546
    Prev
    Next
    INDEX
    Explanations

    drift, relaxation, opening, alertness

    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
    3
    -0.05
     end
    -0.05
    x
    -0.05
    å¤į
    -0.05
    åħ¨è¿ĩç¨ĭ
    -0.05
     End
    -0.05
     -
    -0.05
    åIJ«
    -0.05
    模ç³Ĭ
    -0.05
    4
    -0.05
    POSITIVE LOGITS
    ä¹ĭé«ĺ
    0.07
    ä¸ĵç²¾çī¹æĸ°
    0.07
    apte
    0.07
    ØŃÙĬØ©
    0.07
     fras
    0.07
    รวà¸ĩ
    0.07
    :eq
    0.06
    лее
    0.06
    òn
    0.06
     Tepat
    0.06
    Activations Density 0.001%

    No Known Activations