© 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. 20857
    Prev
    Next
    INDEX
    Explanations

    represented

    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
    ockey
    -0.06
    ar
    -0.06
    ity
    -0.05
    ç»ĦçļĦ
    -0.05
    ivity
    -0.05
    é¾Ļæ¹ĸ
    -0.05
    ité
    -0.05
     typical
    -0.05
    èĵ¬
    -0.05
    iy
    -0.04
    POSITIVE LOGITS
    наÑĢ
    0.08
    ÙĩراÙĨ
    0.07
    jenigen
    0.07
     ulang
    0.07
    ëħIJ
    0.07
    zioni
    0.07
    VELO
    0.06
    chern
    0.06
    ä¹ħèĢĮ
    0.06
    она
    0.06
    Activations Density 0.015%

    No Known Activations