© 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. 21457
    Prev
    Next
    INDEX
    Explanations

    dass, that clauses

    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
     ÑĢода
    -0.08
    anned
    -0.07
    ohn
    -0.07
    neys
    -0.07
    Ø°ÙĨ
    -0.07
    taus
    -0.07
    åĪĩå®ŀå¢ŀ强
    -0.07
    tea
    -0.07
    gers
    -0.06
    est
    -0.06
    POSITIVE LOGITS
    ity
    0.07
    ard
    0.07
    dessen
    0.07
    館
    0.06
    itch
    0.06
    un
    0.06
    halb
    0.06
    ä¸įå¹³
    0.05
    uss
    0.05
    eries
    0.05
    Activations Density 0.001%

    No Known Activations