© 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. 17878
    Prev
    Next
    INDEX
    Explanations

    content type descriptions

    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
    ired
    -0.06
    -0.06
    åģı
    -0.05
    åħ¥æīĭ
    -0.05
    aka
    -0.05
    è¡Į为
    -0.05
    éĢıè¿ĩ
    -0.04
    æĶ¾å¤§
    -0.04
    à¸ĵา
    -0.04
    社ä¼ļ
    -0.04
    POSITIVE LOGITS
    lios
    0.07
     bezig
    0.07
    olato
    0.07
    teres
    0.06
    ÄĽn
    0.06
    hra
    0.06
    mlin
    0.06
    liess
    0.06
    elin
    0.06
     اÙĦرش
    0.06
    Activations Density 0.003%

    No Known Activations