© 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. 18392
    Prev
    Next
    INDEX
    Explanations

    file paths and directories

    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
    åĴĮæľįåĬ¡
    -0.06
    åıĮ缮
    -0.06
    ponder
    -0.06
    ä½łäºĨ
    -0.06
     punt
    -0.06
    unicip
    -0.06
    åĴĮéĹ®é¢ĺ
    -0.05
     боÑĢо
    -0.05
    gon
    -0.05
     polarity
    -0.05
    POSITIVE LOGITS
    listed
    0.06
    à¹Ģลืà¹Īà¸Ńà¸Ļ
    0.06
     luá»ĵng
    0.05
    elig
    0.05
    åľ¨åĪ«äºº
    0.05
    translated
    0.05
    lott
    0.05
    activated
    0.05
    resident
    0.05
    latt
    0.05
    Activations Density 0.026%

    No Known Activations