© 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. 22345
    Prev
    Next
    INDEX
    Explanations

    demonstrate benefit or quality

    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
    åĵģ
    -0.07
    ups
    -0.06
    rowave
    -0.06
    aho
    -0.05
    arta
    -0.05
    igo
    -0.05
    аÑĢи
    -0.05
    hip
    -0.05
    rush
    -0.05
    gether
    -0.05
    POSITIVE LOGITS
    erer
    0.07
    aque
    0.06
    ÑģпоÑģобноÑģÑĤÑĮ
    0.06
    æĢ§åľ°
    0.06
    quila
    0.06
    à¸Ī
    0.06
    panion
    0.05
    erc
    0.05
    eras
    0.05
     reli
    0.05
    Activations Density 0.014%

    No Known Activations