© 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. 17515
    Prev
    Next
    INDEX
    Explanations

    Los Angeles

    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
    st
    -0.06
    ×Ļרת
    -0.06
    ption
    -0.05
    ÑģÑĤÑĢа
    -0.05
    ×Ļר×Ķ
    -0.05
     möj
    -0.05
    éĹ´
    -0.05
    ainty
    -0.05
    —
    -0.04
    Operation
    -0.04
    POSITIVE LOGITS
    arium
    0.08
    imm
    0.06
    ìĦĿ
    0.06
    (mappedBy
    0.06
    ä¸įåı¯åıĬ
    0.06
    çħ§çĿĢ
    0.06
    çIJ¥
    0.06
    zeh
    0.06
     DeV
    0.06
     descar
    0.06
    Activations Density 0.057%

    No Known Activations