© 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. 20885
    Prev
    Next
    INDEX
    Explanations

    medical conditions or descriptive terms

    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
    mÃ¤ÃŁ
    -0.05
    vens
    -0.05
    å¿ĥä¸Ĭ
    -0.05
    ãĥ©
    -0.05
    _workers
    -0.05
    Ñĩе
    -0.05
    使çĶ¨èµ·æĿ¥
    -0.05
    iriam
    -0.05
    对äºİä¸ĢäºĽ
    -0.05
    èĪĴå¿ĥ
    -0.05
    POSITIVE LOGITS
    on
    0.06
    ÙĪغ
    0.06
     handful
    0.06
    å¾ĹåIJį
    0.06
    od
    0.06
    Rh
    0.05
    ftar
    0.05
    hon
    0.05
    åģ¶
    0.05
     albo
    0.05
    Activations Density 0.165%

    No Known Activations