© 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. 17092
    Prev
    Next
    INDEX
    Explanations

    studs, snow, 7, N

    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
     dela
    -0.05
    èģĺ
    -0.05
    iano
    -0.05
    åĮł
    -0.05
    å½ĵä»ĸ们
    -0.05
    etet
    -0.05
    禧
    -0.05
    éĺľ
    -0.05
    loy
    -0.05
    伪
    -0.05
    POSITIVE LOGITS
    occhi
    0.06
    zelt
    0.06
    media
    0.06
    weif
    0.06
    çŁ³æŀĹ
    0.06
     entirety
    0.06
     preoc
    0.05
    ä¸ĢæĹı
    0.05
    icha
    0.05
    çļĦä¸Ģç§įæĸ¹å¼ı
    0.05
    Activations Density 0.045%

    No Known Activations