© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19588
    Prev
    Next
    INDEX
    Explanations

    medical and technical contexts

    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
    illis
    -0.07
    为çĶŁ
    -0.06
    edd
    -0.06
    ermo
    -0.06
    peech
    -0.06
    athers
    -0.06
    ahmen
    -0.06
    пÑĢав
    -0.05
    aro
    -0.05
    ppo
    -0.05
    POSITIVE LOGITS
    èĶĵ
    0.05
    âĢ¥
    0.05
     successive
    0.05
    åį¸
    0.05
    ienia
    0.05
     abdomen
    0.05
    ograph
    0.05
    cida
    0.05
     Mag
    0.05
    é¼ĵèµ·
    0.04
    Activations Density 0.001%

    No Known Activations