© 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. 21990
    Prev
    Next
    INDEX
    Explanations

    countertops, sink, granite

    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
    ä¸ĭå±Ĥ
    -0.05
     inner
    -0.05
    ardia
    -0.05
     tact
    -0.05
     "
    -0.04
     log
    -0.04
    agra
    -0.04
    ä¸Ĭå±Ĥ
    -0.04
     Bennett
    -0.04
    ucken
    -0.04
    POSITIVE LOGITS
    ÑģÑĤеÑģÑĤвенно
    0.07
    ayah
    0.07
    нÑıÑĤие
    0.07
    rok
    0.06
    ä¸ĢæĿ¡é¾Ļ
    0.06
    avat
    0.06
    ufer
    0.06
    积çĶµ
    0.06
    sieme
    0.06
    åľ¨åѦçĶŁ
    0.06
    Activations Density 0.009%

    No Known Activations