© 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. 20973
    Prev
    Next
    INDEX
    Explanations

    code snippets with methods and variables

    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
    çĽĸ
    -0.06
    anni
    -0.06
    ä»ĬæĹ¥
    -0.06
    unned
    -0.06
    Ùĩد
    -0.06
    ä¹ī
    -0.06
     cuc
    -0.05
    umenta
    -0.05
     kov
    -0.05
     cục
    -0.05
    POSITIVE LOGITS
    оÑģÑĤо
    0.06
    æĵįä½ľä¸Ĭ
    0.05
    çħ§å¸¸
    0.05
    ám
    0.05
    lo
    0.05
    çļĦæĵįä½ľ
    0.05
    æĵįä½ľä¸Ń
    0.05
    以ä¸Ĭæĺ¯
    0.05
     repl
    0.05
    éĺ²æĤ£
    0.05
    Activations Density 0.009%

    No Known Activations