© 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. 17736
    Prev
    Next
    INDEX
    Explanations

    random or club

    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
    antan
    -0.06
     عاÙħÙĦ
    -0.06
    ÑĪÑĤа
    -0.05
    å·´åħĭ
    -0.05
    remo
    -0.05
    >>)
    -0.05
    تÙħاÙĨ
    -0.05
    makta
    -0.05
    æŶæĹł
    -0.05
    ä¸Ńä¹Ł
    -0.05
    POSITIVE LOGITS
    ä¸įå¤ĸ
    0.06
    ders
    0.05
    AsStream
    0.05
    vers
    0.05
    utori
    0.05
    VS
    0.05
     trá»įn
    0.05
    iosi
    0.05
    就好
    0.05
    ma
    0.05
    Activations Density 0.305%

    No Known Activations