© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18748
    Prev
    Next
    INDEX
    Explanations

    medical presentations and syndromes

    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
     berin
    -0.08
     bénéfic
    -0.07
     moden
    -0.07
    Äiju
    -0.07
     **>>
    -0.07
    -cond
    -0.07
    éal
    -0.07
    Würt
    -0.07
    seg
    -0.07
    CASCADE
    -0.07
    POSITIVE LOGITS
    0.07
     B
    0.06
    /
    0.05
    1
    0.05
    .
    0.05
     U
    0.05
     K
    0.04
    ä¿ĥ
    0.04
    0
    0.04
    -
    0.04
    Activations Density 0.004%

    No Known Activations