© 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. 17254
    Prev
    Next
    INDEX
    Explanations

    actual name

    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
    ous
    -0.06
    rous
    -0.06
    aru
    -0.05
    åħļ
    -0.05
    éĽĨåĽ¢
    -0.05
    den
    -0.05
    ems
    -0.05
    oga
    -0.05
     expressive
    -0.05
    cat
    -0.05
    POSITIVE LOGITS
    onnal
    0.06
    sko
    0.06
    ibraltar
    0.06
    áĢĸáĢ¼
    0.06
    åĽ°éļ¾åĴĮéĹ®é¢ĺ
    0.06
    Verk
    0.06
     periodically
    0.06
    ä¸įæĻĤ
    0.06
    ovil
    0.06
    abschluss
    0.06
    Activations Density 0.001%

    No Known Activations