© 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. 21646
    Prev
    Next
    INDEX
    Explanations

    and followed by a noun

    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
     exempl
    -0.06
    身åŃIJ
    -0.05
     ocul
    -0.05
    çĢ
    -0.05
    æľ¬äººåľ¨
    -0.05
     (
    -0.05
    æĪijåı¯ä»¥
    -0.05
     accompanied
    -0.05
    ий
    -0.05
    é£ŀæĿ¥
    -0.04
    POSITIVE LOGITS
    estet
    0.07
    anmar
    0.07
    веÑĢÑĪенно
    0.07
    egative
    0.06
    vard
    0.06
    åį´è¦ģ
    0.06
     GIVEN
    0.06
    ócr
    0.06
    urian
    0.06
    ulasi
    0.06
    Activations Density 0.028%

    No Known Activations