© 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. 17884
    Prev
    Next
    INDEX
    Explanations

    depends on

    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
     sometimes
    -0.06
     zust
    -0.05
    æľīçļĦ
    -0.05
    æĹ¢æľī
    -0.05
    åIJĮæĹ¥
    -0.05
    contro
    -0.05
    çİĭä¹ĭ
    -0.05
    æłĩåĩĨåĮĸ
    -0.05
    osit
    -0.05
    manage
    -0.05
    POSITIVE LOGITS
     Anch
    0.06
    æīĵæī®
    0.05
    ifest
    0.05
    å°ıéĿĴ
    0.05
    -plugins
    0.05
    kait
    0.05
    çĺ¸
    0.05
    heels
    0.05
    åħ¬æŃ£
    0.05
    轿
    0.05
    Activations Density 0.001%

    No Known Activations