© 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
    2. Qwen3.5-4B
    3. 15-RES-MATRYOSHKA-65K
    4. 17280
    Prev
    Next
    INDEX
    Explanations

    quotation marks ending a statement

    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
    लà¥į
    -0.05
    çϾ年
    -0.05
    ling
    -0.05
     tack
    -0.05
     bottoms
    -0.05
    &R
    -0.05
    ostal
    -0.05
    atural
    -0.05
    åĮĸæĪIJ
    -0.05
     tor
    -0.05
    POSITIVE LOGITS
    æĹ¥åħ¬å¸ĥ
    0.07
    çĮ¬
    0.06
    æĬĺä¸įæī£
    0.06
     Klimaan
    0.06
    æĹ¥å®£å¸ĥ
    0.06
    åIJĦå¤Ħ
    0.06
    perms
    0.06
    太差
    0.06
    gend
    0.06
    nese
    0.06
    Activations Density 0.003%

    No Known Activations