© 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. 21244
    Prev
    Next
    INDEX
    Explanations

    launched on

    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
    åħĪè¿Ľ
    -0.06
     UNUSED
    -0.06
    æĺ§
    -0.06
    ä¸İ被åijĬ
    -0.06
    ковод
    -0.06
    eway
    -0.06
    人åĽŀå¤į
    -0.06
    kaç
    -0.06
    merce
    -0.06
     advancing
    -0.06
    POSITIVE LOGITS
    åĽ´ç»ķçĿĢ
    0.05
    ider
    0.05
    ARCH
    0.05
    archit
    0.05
     basically
    0.05
    heet
    0.05
    aida
    0.05
    æĪIJåħ¨
    0.05
    ç´§ç´§åĽ´ç»ķ
    0.05
    ios
    0.05
    Activations Density 0.001%

    No Known Activations