© 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. 19202
    Prev
    Next
    INDEX
    Explanations

    in the

    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
     peculi
    -0.07
    gh
    -0.07
    å¦Ĥæĺ¯
    -0.06
     Magnes
    -0.06
    ì£¼ë¡ľ
    -0.06
    akta
    -0.06
    ogh
    -0.06
    fts
    -0.06
    omma
    -0.06
    assen
    -0.06
    POSITIVE LOGITS
    0.07
     fur
    0.05
    lene
    0.05
     $\
    0.05
     کسÛĮ
    0.05
    /to
    0.05
    è£ģ
    0.05
    з
    0.05
     spe
    0.04
    wife
    0.04
    Activations Density 0.001%

    No Known Activations