© 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. 17925
    Prev
    Next
    INDEX
    Explanations

    code statement or document end

    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
    requ
    -0.07
    kit
    -0.07
    uppy
    -0.07
     Maire
    -0.06
    alui
    -0.06
    ntag
    -0.06
    æµ·æ¶Ľ
    -0.06
    pollo
    -0.06
    gaan
    -0.06
    è·¯åŃIJ
    -0.06
    POSITIVE LOGITS
    0.06
     de
    0.06
    ä¹İ
    0.06
    angan
    0.06
    uestion
    0.05
    aka
    0.05
    ä¹Łç§°ä¸º
    0.05
    åı¯æĢľ
    0.05
     Collective
    0.05
    ç»Ŀ
    0.05
    Activations Density 0.001%

    No Known Activations