© 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. 21669
    Prev
    Next
    INDEX
    Explanations

    high temperatures or speeds

    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
     ανÏĦί
    -0.06
    edar
    -0.06
     наÑħод
    -0.05
    antos
    -0.05
    asaran
    -0.05
    éĩıåĬĽ
    -0.05
    æĮīåħ¶
    -0.05
    éĢĤéĩıçļĦ
    -0.05
    äºŃ
    -0.05
    æĹģ人
    -0.05
    POSITIVE LOGITS
    UDA
    0.06
     KHO
    0.06
    zem
    0.06
     impecc
    0.06
    endo
    0.05
    жаÑĤ
    0.05
    ç»ıèIJ¥çĬ¶æĢģ
    0.05
    abor
    0.05
    iving
    0.05
    ļĮ
    0.05
    Activations Density 0.028%

    No Known Activations