© 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. 22096
    Prev
    Next
    INDEX
    Explanations

    do not / don't

    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
     itself
    -0.06
    ising
    -0.05
     divers
    -0.05
     herself
    -0.05
    価
    -0.05
    ä¸įå°½
    -0.05
     s
    -0.05
     ~
    -0.05
     editorial
    -0.05
     ing
    -0.05
    POSITIVE LOGITS
    rench
    0.07
     disminu
    0.07
    ]-$
    0.06
    æĪIJåįĥ
    0.06
    éļ¶å±ŀ
    0.06
     ×ĸ×ķ
    0.06
    æĪIJ大
    0.06
    vall
    0.06
    æĪIJ
    0.06
     cerem
    0.06
    Activations Density 0.129%

    No Known Activations