© 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. 21074
    Prev
    Next
    INDEX
    Explanations

    field, section, context, implementation

    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
    常åĬ¡çIJĨäºĭ
    -0.06
     verk
    -0.06
    ä¸ĬçŃī
    -0.06
    ä¼ļä¸Ĭ
    -0.05
    aupts
    -0.05
    à¹īาว
    -0.05
    ">ÃĹ</
    -0.05
    ograma
    -0.05
    irk
    -0.05
    åı¯ä»İ
    -0.05
    POSITIVE LOGITS
    &,
    0.06
    ere
    0.06
    kana
    0.05
    zer
    0.05
     tamp
    0.05
    è½®çļĦ
    0.05
    士ãģ®
    0.05
    .*,
    0.05
    าà¸ĩ
    0.05
    erosis
    0.05
    Activations Density 0.001%

    No Known Activations