© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19621
    Prev
    Next
    INDEX
    Explanations

    minor amounts or degrees

    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
    å°ı
    -0.06
    æļĤè¡Į
    -0.06
    ä»»éĢī
    -0.06
    ysel
    -0.06
    çŁŃ
    -0.06
    оÑĢоÑĤ
    -0.06
    çıł
    -0.05
    unload
    -0.05
    é«ĺ
    -0.05
    åįĬ
    -0.05
    POSITIVE LOGITS
    inen
    0.07
    rakt
    0.06
     nationwide
    0.06
    ines
    0.06
    iner
    0.06
     statewide
    0.05
    atia
    0.05
    ace
    0.05
    inis
    0.05
    adesh
    0.05
    Activations Density 0.091%

    No Known Activations