© 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. 17068
    Prev
    Next
    INDEX
    Explanations

    two or three of

    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
     människ
    -0.06
    riel
    -0.06
    æĶ¾çŁ¢
    -0.05
    rvine
    -0.05
    allon
    -0.05
    orde
    -0.05
    æĪij们æ¯ı个人
    -0.05
    æ¯Ķ以åīį
    -0.05
     Prairie
    -0.05
    æ¯Ķåħ¶ä»ĸ
    -0.05
    POSITIVE LOGITS
    chen
    0.06
    ucar
    0.06
    ê¸Īì§Ģ
    0.06
    afür
    0.06
     lingam
    0.06
    ingly
    0.06
    è¯Ŀ说
    0.05
    uc
    0.05
    ikal
    0.05
    Ùĩر
    0.05
    Activations Density 0.009%

    No Known Activations