© 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. 17701
    Prev
    Next
    INDEX
    Explanations

    `static void`

    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
    audi
    -0.07
    ä¸Ģè¨Ģ
    -0.06
    weisen
    -0.06
    -handed
    -0.06
    为ä¹ĭ
    -0.06
    åĤ»
    -0.06
    dea
    -0.06
    Verk
    -0.06
     εÏĢÎŃ
    -0.06
    ائÙĬØ©
    -0.06
    POSITIVE LOGITS
    åıī
    0.05
    ä¸įåĪ°äºĨ
    0.05
    å½¢
    0.05
    ä¸įç®Ĺ
    0.05
    én
    0.05
    çļĦæľĭåıĭ们
    0.05
    çĸ¼
    0.05
    好æľĭåıĭ
    0.05
    xn
    0.04
    gren
    0.04
    Activations Density 0.004%

    No Known Activations