© 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. 17479
    Prev
    Next
    INDEX
    Explanations

    Making

    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
     ðŁĺĢ
    -0.06
    ander
    -0.06
    ãģ°ãģĭãĤĬ
    -0.06
    ä¸Ĭ马
    -0.06
    usnya
    -0.06
    滥
    -0.05
    éĹŃä¸Ĭçľ¼çĿĽ
    -0.05
     ria
    -0.05
     antic
    -0.05
    vole
    -0.05
    POSITIVE LOGITS
     Struk
    0.05
    æķ´ä¸ªéĹ®é¢ĺ
    0.05
    imb
    0.05
    æĸĩ
    0.05
    çĦ¶
    0.05
    intent
    0.05
    æŃ¥éª¤
    0.05
    illos
    0.05
    å°Ĩäºİ
    0.05
    unger
    0.05
    Activations Density 0.007%

    No Known Activations