© 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. 18009
    Prev
    Next
    INDEX
    Explanations

    daily

    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
    第äºĮæĿ¡
    -0.06
    formed
    -0.05
    +
    -0.05
    踩
    -0.05
    azz
    -0.05
     numerous
    -0.05
    æŃ»ä¸į
    -0.05
    åĿı
    -0.05
     exposition
    -0.05
     formation
    -0.05
    POSITIVE LOGITS
    èĩªçIJĨ
    0.07
    ikli
    0.07
    ãģ¾ãģ¾
    0.07
    elda
    0.06
    atto
    0.06
    elper
    0.06
    anam
    0.06
    icto
    0.06
    pasar
    0.06
    èĩªå¦Ĥ
    0.06
    Activations Density 0.041%

    No Known Activations