© 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. 22337
    Prev
    Next
    INDEX
    Explanations

    variable declaration or usage

    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
    tab
    -0.05
    cedes
    -0.05
     ded
    -0.05
    get
    -0.05
     members
    -0.05
    oly
    -0.05
    åľ°ä¸Ĭ
    -0.05
    è§Ħå¾ĭ
    -0.05
     get
    -0.05
    del
    -0.05
    POSITIVE LOGITS
    æĺİå¹´çļĦ
    0.07
    uard
    0.07
    gars
    0.07
    gegen
    0.06
    è¿ĶåĽŀåĪĹ表
    0.06
    returned
    0.06
    å°Ĩ对
    0.06
    æĸ°å±Ģ
    0.06
    attles
    0.06
    riques
    0.06
    Activations Density 0.004%

    No Known Activations