© 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. 22081
    Prev
    Next
    INDEX
    Explanations

    numbers and menu items

    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
    ĥ
    -0.06
    ç´¢
    -0.05
    poses
    -0.05
    éĶĢ
    -0.05
     Lennon
    -0.05
    ä»Ģä¹Īåľ°æĸ¹
    -0.05
    ä½ij
    -0.05
    æľī人
    -0.05
    LLU
    -0.05
     Montes
    -0.05
    POSITIVE LOGITS
    Ñģко
    0.06
    Duplicates
    0.06
    ç°ĩ
    0.06
     *}
    0.06
    icing
    0.06
    Ñĥжи
    0.06
    æĽ´æĸ°çļĦ
    0.06
    ÙĪجÙĩ
    0.06
    our
    0.06
    Ùģر
    0.06
    Activations Density 0.002%

    No Known Activations