© 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. 21098
    Prev
    Next
    INDEX
    Explanations

    once busy, d(m(f)), male parent

    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
    å°Ĩå°±
    -0.07
     kav
    -0.07
    chr
    -0.07
    rais
    -0.07
    elde
    -0.06
     chr
    -0.06
    ,eg
    -0.06
    urma
    -0.06
    yani
    -0.06
    áĢŃáĢ¯áĢĦáĢº
    -0.06
    POSITIVE LOGITS
     breakdown
    0.05
    åĸľæĢĴ
    0.05
    ench
    0.05
    ump
    0.05
    __
    0.05
    ç¥ŀç§ĺçļĦ
    0.04
    mute
    0.04
     -
    0.04
    éĢĢ
    0.04
    _
    0.04
    Activations Density 0.001%

    No Known Activations