© 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. 20844
    Prev
    Next
    INDEX
    Explanations

    diseases

    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
     dele
    -0.07
    æĪ¿
    -0.06
     rather
    -0.05
    inho
    -0.05
    mero
    -0.05
    reg
    -0.05
    arden
    -0.05
    cho
    -0.05
     pres
    -0.05
    /library
    -0.05
    POSITIVE LOGITS
    amous
    0.06
    ä¸ĢçŃ¹
    0.06
    িব
    0.06
    arious
    0.06
    å®ĪåĪĻ
    0.06
    edicine
    0.06
    olik
    0.06
    istu
    0.06
    ané
    0.06
    ispond
    0.06
    Activations Density 0.029%

    No Known Activations