© 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. 21507
    Prev
    Next
    INDEX
    Explanations

    setting innerHTML

    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
    aurus
    -0.07
    ure
    -0.06
    jamin
    -0.06
    enÃŃ
    -0.05
    prototype
    -0.05
    æ´¼
    -0.05
    ÑİÑĢи
    -0.05
    stä
    -0.05
    å¾Īåı¯èĥ½
    -0.05
    rous
    -0.05
    POSITIVE LOGITS
    ãĥĬãĥĥãĥĹ
    0.07
    isp
    0.07
    oxic
    0.06
    emiz
    0.06
    ÑĤовÑĭе
    0.06
    ÑĢек
    0.06
    éĵł
    0.06
    ivit
    0.05
     embargo
    0.05
    ÙĨدر
    0.05
    Activations Density 0.002%

    No Known Activations