© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17189
    Prev
    Next
    INDEX
    Explanations

    web page tags and medical terms

    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
    acher
    -0.06
    olib
    -0.06
    ail
    -0.06
    ony
    -0.06
    ä¸ĭåIJĮ
    -0.06
    ONOM
    -0.06
    pany
    -0.05
    ist
    -0.05
     pire
    -0.05
    ä½ķ
    -0.05
    POSITIVE LOGITS
    inete
    0.06
    pum
    0.06
    -St
    0.06
    üs
    0.06
    Ñģол
    0.05
     Ñģол
    0.05
    èµ°éģį
    0.05
    lox
    0.05
    浸
    0.05
    ниÑģ
    0.05
    Activations Density 0.015%

    No Known Activations