© 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. 20188
    Prev
    Next
    INDEX
    Explanations

    relax

    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
    æ¦Ĩ
    -0.06
    olds
    -0.06
    รà¸ĩ
    -0.06
    åıįéĿ¢
    -0.06
    èĥ¡æĢĿ
    -0.06
    ool
    -0.06
    éĹĬ
    -0.06
    èĨľçĤİ
    -0.06
     tiba
    -0.06
    idora
    -0.06
    POSITIVE LOGITS
     conserv
    0.05
    çĿĢåij¢
    0.05
     fas
    0.05
     اÙĦØ¥Ùħ
    0.05
    ced
    0.05
    çģµ
    0.05
     Schl
    0.05
     liter
    0.05
     met
    0.05
    sequ
    0.05
    Activations Density 0.006%

    No Known Activations