© 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. 22350
    Prev
    Next
    INDEX
    Explanations

    code header inclusions

    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
    ihat
    -0.07
    ovid
    -0.06
     personalised
    -0.06
     Patr
    -0.06
    _personal
    -0.06
    Patr
    -0.06
    Fans
    -0.06
    rof
    -0.06
    lod
    -0.06
    ëħĦìĿ´
    -0.06
    POSITIVE LOGITS
    avanaugh
    0.05
     come
    0.05
    parable
    0.05
     transformation
    0.04
    uger
    0.04
    ren
    0.04
    й
    0.04
     Rage
    0.04
     L
    0.04
    _l
    0.04
    Activations Density 0.256%

    No Known Activations