© 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. 21241
    Prev
    Next
    INDEX
    Explanations

    multiple instances

    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
    æ¯ĶåĪ©
    -0.06
    å±ĢéĿ¢
    -0.05
    çľ¾
    -0.05
    .length
    -0.05
    Interactive
    -0.05
     interact
    -0.05
     individually
    -0.05
    äºī缸
    -0.05
    ragon
    -0.04
    åIJĦæĸ¹
    -0.04
    POSITIVE LOGITS
    emps
    0.06
    åIJĮæĹ¥
    0.06
    tures
    0.06
    -ra
    0.06
    utura
    0.06
    laÄį
    0.06
    iston
    0.06
    atura
    0.06
     Exec
    0.06
    adra
    0.06
    Activations Density 0.170%

    No Known Activations