© 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. 20212
    Prev
    Next
    INDEX
    Explanations

    statement summary

    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
    encontre
    -0.07
    itably
    -0.07
    amaz
    -0.07
    oppi
    -0.06
    çī¹éĴ¢
    -0.06
    amat
    -0.06
    ãģªãģįãĤĥ
    -0.06
    unya
    -0.06
    请ç¨įåĢĻ
    -0.06
    ä¸ĩ个
    -0.06
    POSITIVE LOGITS
    оÑĤ
    0.05
    sche
    0.05
     respective
    0.05
     âģ
    0.05
     officielle
    0.05
     final
    0.05
    yas
    0.05
    ÑĤÑı
    0.05
    let
    0.05
     official
    0.05
    Activations Density 0.002%

    No Known Activations