© 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. 21261
    Prev
    Next
    INDEX
    Explanations

    hurt

    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
    âĢĮ
    -0.05
    ç«ĭæĸ°
    -0.05
    ouncer
    -0.05
    æ°
    -0.05
     thôi
    -0.05
    诸
    -0.05
    ativi
    -0.05
    ((_
    -0.05
    etween
    -0.05
    =""></
    -0.04
    POSITIVE LOGITS
    tec
    0.08
    ÑĢÑĥп
    0.08
    pedo
    0.07
    hya
    0.07
    cita
    0.07
    tual
    0.07
    æ³½æ°ij
    0.07
    ragen
    0.07
    ersen
    0.07
    craft
    0.06
    Activations Density 0.002%

    No Known Activations