© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18537
    Prev
    Next
    INDEX
    Explanations

    select or selection

    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
    hte
    -0.06
    ivism
    -0.06
    ivist
    -0.06
    htë
    -0.06
    utor
    -0.06
    thro
    -0.06
    æĿ¥è¿ĩ
    -0.06
    æ¯ıä½į
    -0.06
    γα
    -0.06
    uates
    -0.06
    POSITIVE LOGITS
    ادÛĮ
    0.06
    ast
    0.06
    åħ¨åĽ½
    0.06
    eras
    0.05
    ä¾Ŀæ³ķæ²»
    0.05
    åĨħå¤ĸ
    0.05
    æĭ¿ä¸ĭ
    0.05
    еÑģÑģ
    0.05
     củ
    0.05
    åıĸå¾ĹçļĦ
    0.05
    Activations Density 0.008%

    No Known Activations