© 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. 17470
    Prev
    Next
    INDEX
    Explanations

    started a the : at Memories roll

    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
    åĪ¶éĢł
    -0.06
    æķ£
    -0.06
     wag
    -0.05
    dex
    -0.05
    elog
    -0.05
     rico
    -0.05
    çĶŁåij½å®īåħ¨
    -0.05
    onom
    -0.05
     shalat
    -0.05
    家çļĦ
    -0.05
    POSITIVE LOGITS
    neau
    0.05
     avv
    0.05
    rends
    0.05
    lesc
    0.05
    [method
    0.05
    æ¯Ķè¼ĥ好
    0.05
    بÙĦ
    0.05
     [&](
    0.05
    ayan
    0.05
    {}]
    0.05
    Activations Density 0.001%

    No Known Activations