© 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. 17640
    Prev
    Next
    INDEX
    Explanations

    units of measure

    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
    imm
    -0.06
    en
    -0.06
    u
    -0.06
    attr
    -0.06
    abi
    -0.05
    elastic
    -0.05
    in
    -0.05
    رÙĬبا
    -0.05
    ä½įçļĦ
    -0.05
    uan
    -0.05
    POSITIVE LOGITS
    åħļè§Ħ
    0.06
    ÑĩеÑĢед
    0.06
    ufreq
    0.06
    ÙĬÙĦØ©
    0.06
    strup
    0.06
    iful
    0.06
    欢è¿İ大家éĺħ读
    0.05
     theirs
    0.05
    zgl
    0.05
    tec
    0.05
    Activations Density 0.041%

    No Known Activations