© 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. 21626
    Prev
    Next
    INDEX
    Explanations

    assertion checks

    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
    临
    -0.06
    stieg
    -0.06
     demais
    -0.06
    ellig
    -0.05
    оÑģоб
    -0.05
    alet
    -0.05
    æĸ°åĬłåĿ¡
    -0.05
    roh
    -0.05
    jal
    -0.05
    /th
    -0.05
    POSITIVE LOGITS
    夷
    0.06
    ç½ķ
    0.06
    ekat
    0.06
    etime
    0.06
    ä½Ĩä¸įéĻIJäºİ
    0.05
    oline
    0.05
    çªģåĩºçļĦ
    0.05
    rais
    0.05
    isco
    0.05
    ¯
    0.05
    Activations Density 0.008%

    No Known Activations