© 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. 22218
    Prev
    Next
    INDEX
    Explanations

    export item, Jacob name, King name, BL code

    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
    糯
    -0.06
    unction
    -0.06
    alic
    -0.05
    klar
    -0.05
    ánt
    -0.05
    éĴĵé±¼
    -0.05
    дÑĭÒĽ
    -0.05
     otur
    -0.05
    è¿ĩé«ĺ
    -0.05
    abc
    -0.05
    POSITIVE LOGITS
    aye
    0.06
    ay
    0.06
    éļIJèĹıçļĦ
    0.06
    è¿Ķ
    0.05
    voz
    0.05
    èĹıçļĦ
    0.05
    ä¸ĭåįĬ
    0.05
    èĹı
    0.05
    selection
    0.05
    -options
    0.05
    Activations Density 0.007%

    No Known Activations