© 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. 16815
    Prev
    Next
    INDEX
    Explanations

    following second person pronouns

    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
    表çİ°åľ¨
    -0.06
    à¹ĥห
    -0.06
    æݧ
    -0.05
    人åĿĩåı¯
    -0.05
    ×Ķ׾
    -0.05
    lerce
    -0.05
     пÑĢоÑĨеÑģÑģа
    -0.05
    uada
    -0.05
    igators
    -0.05
    cred
    -0.05
    POSITIVE LOGITS
    undert
    0.05
     https
    0.05
    ully
    0.05
    çĶ¨ä¹¦
    0.05
    tickets
    0.05
    https
    0.05
    åIJĥåĸĿ
    0.05
    INDER
    0.05
    ilda
    0.05
    ÑģполÑĮзÑĥ
    0.05
    Activations Density 0.006%

    No Known Activations