© 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. 21107
    Prev
    Next
    INDEX
    Explanations

    .

    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
     scope
    -0.06
    apu
    -0.05
    yser
    -0.05
    TY
    -0.05
    驹
    -0.05
    Boolean
    -0.05
    驼
    -0.05
    _PHYS
    -0.05
     Ùħر
    -0.05
    tuu
    -0.05
    POSITIVE LOGITS
    æŃ£å¸¸è¿IJè¡Į
    0.06
    ench
    0.06
    è£ħçĿĢ
    0.06
    elola
    0.05
     innoc
    0.05
    ÑĪке
    0.05
    <=$
    0.05
    èĪĴ
    0.05
    ä¸įçŁ¥æĥħ
    0.05
     vÃŃa
    0.05
    Activations Density 0.016%

    No Known Activations