© 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. 21423
    Prev
    Next
    INDEX
    Explanations

    examples and wherein clauses

    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
    ude
    -0.05
     whichever
    -0.05
    天çİĭ
    -0.05
    ym
    -0.05
     agré
    -0.05
     découvrez
    -0.05
    åIJĵå¾Ĺ
    -0.04
     bénéfic
    -0.04
    rack
    -0.04
    ents
    -0.04
    POSITIVE LOGITS
     (...
    0.07
    .bb
    0.06
    ONSE
    0.06
    ccion
    0.06
    æĺ¯æľī
    0.06
    ابع
    0.06
    etter
    0.05
     batt
    0.05
    æ·¹
    0.05
    ungkan
    0.05
    Activations Density 0.998%

    No Known Activations