© 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. 17088
    Prev
    Next
    INDEX
    Explanations

    URLs and code comments

    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
    èıģ
    -0.05
    æĢ§
    -0.05
    alf
    -0.05
    t
    -0.05
    c
    -0.05
    ild
    -0.05
    æĺ¨
    -0.05
    ton
    -0.04
    b
    -0.04
    èī²
    -0.04
    POSITIVE LOGITS
    ئÙĩ
    0.07
    itzer
    0.07
     YYS
    0.07
    reating
    0.07
    åıªæıIJä¾Ľ
    0.06
    eyed
    0.06
    ptype
    0.06
    esu
    0.06
    ä»ħæıIJä¾Ľ
    0.06
    ÑĦо
    0.06
    Activations Density 0.001%

    No Known Activations