© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19128
    Prev
    Next
    INDEX
    Explanations

    count how many times

    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
     Mark
    -0.07
     Z
    -0.06
    ç«Ļ
    -0.05
     Fresh
    -0.05
    isch
    -0.05
    /Main
    -0.05
    /D
    -0.05
     D
    -0.05
     z
    -0.05
     Diam
    -0.05
    POSITIVE LOGITS
     Teixe
    0.06
    olari
    0.06
     sexi
    0.06
    asitas
    0.06
    ÙĪÙħÙĩ
    0.06
    netinet
    0.06
    à¹Ģà¸Ķียว
    0.06
     menun
    0.06
    丢æİī
    0.06
     ÑĥÑģÑĥ
    0.06
    Activations Density 0.027%

    No Known Activations