© 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. 17471
    Prev
    Next
    INDEX
    Explanations

    titles starting with "a" or "s"

    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
    igur
    -0.05
    饿
    -0.05
     ëĭ¤ìĿĮìĿĢ
    -0.05
    zoek
    -0.05
    iga
    -0.05
    欧å§Ĩ
    -0.05
    edd
    -0.05
    çĽ¸ä¼ł
    -0.05
     cinemat
    -0.05
    untut
    -0.05
    POSITIVE LOGITS
    çĽ¡
    0.06
     dividing
    0.05
    سÙĬÙħ
    0.05
    _virtual
    0.05
     Div
    0.05
    aszt
    0.05
     mess
    0.05
     pertinent
    0.05
    greg
    0.05
    å°½åħ¶
    0.05
    Activations Density 0.242%

    No Known Activations