© 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. 22327
    Prev
    Next
    INDEX
    Explanations

    `a` or `b` subsequences

    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
    íĶĦë¡ľ
    -0.05
    lø
    -0.05
    inne
    -0.05
    æıIJåĩº
    -0.05
    大ä¸Ń
    -0.05
    åt
    -0.05
    éĢīå®ļ
    -0.05
    æıIJåĩºçļĦ
    -0.05
    NotFoundError
    -0.05
    utoff
    -0.05
    POSITIVE LOGITS
    ys
    0.06
    ths
    0.06
    eld
    0.06
    aced
    0.06
    ansfer
    0.06
    ng
    0.06
    gang
    0.05
    ãĥ©ãĥ³ãĤ¹
    0.05
    ä¼Ĺ
    0.05
    mals
    0.05
    Activations Density 0.135%

    No Known Activations