© 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. 21369
    Prev
    Next
    INDEX
    Explanations

    exclusively

    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
    hyd
    -0.06
    gart
    -0.06
    yc
    -0.05
    erlo
    -0.05
    holz
    -0.05
    ä¸ĢæĹ¥
    -0.05
    اÙĨÙĪÙĨ
    -0.05
    æľªæľī
    -0.05
    ¸
    -0.05
     carto
    -0.05
    POSITIVE LOGITS
    座çļĦ
    0.07
    maÃŁ
    0.05
     suited
    0.05
    çıŃä¼ļ
    0.05
    нÑıÑĤ
    0.05
     aj
    0.05
    istici
    0.05
    åĽ°å¢ĥ
    0.05
    座
    0.05
    æīĵèµ·
    0.05
    Activations Density 0.004%

    No Known Activations