© 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. 20401
    Prev
    Next
    INDEX
    Explanations

    men and females

    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
     here
    -0.05
     Hill
    -0.05
    annot
    -0.05
    here
    -0.05
    irus
    -0.05
    åŁºç¡Ģ
    -0.05
     part
    -0.05
    uar
    -0.05
    b
    -0.05
    irim
    -0.05
    POSITIVE LOGITS
    太好
    0.06
    eht
    0.06
    [url
    0.06
    stig
    0.06
    _Collections
    0.06
     predecess
    0.06
    niest
    0.06
     [[
    0.06
    خصة
    0.06
     Patr
    0.05
    Activations Density 0.275%

    No Known Activations