© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19076
    Prev
    Next
    INDEX
    Explanations

    t-shirt and shorts

    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
    менÑıÑĤÑĮ
    -0.06
    èģĺ
    -0.06
    Ñģловно
    -0.06
    å¼Ģå§ĭåIJİ
    -0.06
    mate
    -0.06
    resto
    -0.06
    chten
    -0.06
    Alchemy
    -0.06
     bind
    -0.06
    Q
    -0.05
    POSITIVE LOGITS
    erve
    0.06
    ergia
    0.05
    LBL
    0.05
     plain
    0.05
    ises
    0.05
     incendi
    0.05
     اÙĦعاب
    0.05
    LENGTH
    0.05
    utters
    0.05
    亲åĪĩ
    0.05
    Activations Density 0.003%

    No Known Activations