© 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. 22006
    Prev
    Next
    INDEX
    Explanations

    names, dates, policy, defects

    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
     дека
    -0.05
    akt
    -0.05
    -0.05
    çļĦæľºä¼ļ
    -0.05
    iode
    -0.05
     saud
    -0.05
     ute
    -0.05
    구íķĺê³ł
    -0.05
    åįĥ家
    -0.05
    追éļı
    -0.05
    POSITIVE LOGITS
    ensor
    0.07
    leman
    0.06
     ìłIJìĹIJìĦľ
    0.06
    leit
    0.06
     Gors
    0.06
    warf
    0.05
    jol
    0.05
    lare
    0.05
    hall
    0.05
    çļĦä¸ĢéĿ¢
    0.05
    Activations Density 0.024%

    No Known Activations