© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20503
    Prev
    Next
    INDEX
    Explanations

    belongs to

    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
    ãģĤãĤĮãģ°
    -0.07
    rant
    -0.06
    ledes
    -0.06
    оÑģÑĤ
    -0.06
    uality
    -0.05
    ra
    -0.05
    isable
    -0.05
    ë§ĪìŀIJ
    -0.05
    idades
    -0.05
    oux
    -0.05
    POSITIVE LOGITS
    centage
    0.06
     sake
    0.06
    ืà¸Ń
    0.06
    æŶåĢĻ
    0.06
     جÙĩØ©
    0.06
    ogne
    0.06
    dorf
    0.06
    ạng
    0.06
     Dodatkowo
    0.06
     fray
    0.06
    Activations Density 0.009%

    No Known Activations