© 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
    2. Qwen3.5-4B
    3. 15-RES-MATRYOSHKA-65K
    4. 21514
    Prev
    Next
    INDEX
    Explanations

    light colors

    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
    anes
    -0.07
    æĹ¥è¡¨ç¤º
    -0.07
    atre
    -0.07
    ÅĤek
    -0.07
     espet
    -0.07
    prib
    -0.07
    (mon
    -0.07
     <![
    -0.07
    ghan
    -0.07
    èĩªè¾¾
    -0.07
    POSITIVE LOGITS
     
    0.06
    1
    0.06
    M
    0.06
    H
    0.06
    2
    0.06
    in
    0.05
    B
    0.05
    ev
    0.05
    /
    0.05
    X
    0.05
    Activations Density 0.004%

    No Known Activations