© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16631
    Prev
    Next
    INDEX
    Explanations

    credit Horace

    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
    Negative Logits
    ams
    -0.06
    les
    -0.05
    ri
    -0.05
    æł¹æľ¬æĹłæ³ķ
    -0.05
    @
    -0.05
    oral
    -0.04
    ת×Ļ
    -0.04
    pg
    -0.04
    po
    -0.04
    ontos
    -0.04
    POSITIVE LOGITS
    inus
    0.07
    tua
    0.07
    arily
    0.07
    翼翼
    0.06
    [âĢ¦
    0.06
    #c
    0.06
    ÑĩенÑĸ
    0.06
    /Internal
    0.06
    ÑģÑĤÑĮ
    0.06
    ï¼ļ%
    0.06
    Activations Density 0.002%

    No Known Activations