© 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. 18562
    Prev
    Next
    INDEX
    Explanations

    end punctuation

    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
    ä¸į足以
    -0.06
    级
    -0.06
    è¾Ľ
    -0.05
     доÑģÑĤ
    -0.05
    pul
    -0.05
    érist
    -0.05
    /Y
    -0.05
    praw
    -0.05
     íķł
    -0.05
     genoeg
    -0.05
    POSITIVE LOGITS
    appy
    0.07
     تØŃÙĤÙĤ
    0.06
    ä¿Ŀè¯ģåħ¶
    0.06
    :error
    0.06
    lese
    0.06
    åħ¨ä¼ļç²¾ç¥ŀ
    0.06
    大æľīåı¯ä¸º
    0.06
    èIJ©
    0.06
    arana
    0.06
    uron
    0.06
    Activations Density 0.024%

    No Known Activations