© 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. 18170
    Prev
    Next
    INDEX
    Explanations

    HTML metadata and parameters

    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
    æ°ij
    -0.06
    ostar
    -0.06
    ä¸įåı¯
    -0.05
    stag
    -0.05
    åľ°ä¸ĭ
    -0.05
    Ø´Ùħ
    -0.05
    apos
    -0.05
    emp
    -0.05
     zust
    -0.05
    awning
    -0.05
    POSITIVE LOGITS
    urement
    0.06
    tienen
    0.06
    s
    0.06
    Ú©ÙĨ
    0.06
    éĹ´çļĦ
    0.06
    ura
    0.05
    adh
    0.05
    áŀ¶áŀĽ
    0.05
    able
    0.05
     lojas
    0.05
    Activations Density 0.158%

    No Known Activations