© 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. 21604
    Prev
    Next
    INDEX
    Explanations

    protein amounts

    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
    érées
    -0.06
    roph
    -0.06
    xies
    -0.05
     }}}
    -0.05
    érés
    -0.05
    ÙĦائ
    -0.05
    Defined
    -0.05
    íĩ´
    -0.05
    æ³Ľ
    -0.05
    åIJĪçIJĨåĮĸ
    -0.05
    POSITIVE LOGITS
    éĥ¨
    0.06
    irc
    0.05
    âĢ¦but
    0.05
    struct
    0.05
    æľīå½±åĵį
    0.05
    ä¸ĢæĿ¡
    0.05
    sche
    0.05
    æµ
    0.05
    ilver
    0.05
    SV
    0.05
    Activations Density 0.001%

    No Known Activations