© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22588
    Prev
    Next
    INDEX
    Explanations

    mental health

    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
    Negative Logits
    wad
    -0.07
     keh
    -0.06
    odate
    -0.06
     collet
    -0.06
    иÑģк
    -0.06
    æľīåĬĽçļĦ
    -0.06
    uwe
    -0.06
    ä»ĸ们æĺ¯
    -0.06
    atorium
    -0.06
    éģĵçIJĨ
    -0.06
    POSITIVE LOGITS
    æ¶ķ
    0.05
     Peters
    0.04
    бина
    0.04
    ational
    0.04
    vis
    0.04
    ra
    0.04
    æ±ī
    0.04
     kiá»ĩt
    0.04
    ĥ
    0.04
    bits
    0.04
    Activations Density 0.206%

    No Known Activations