© 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. 20197
    Prev
    Next
    INDEX
    Explanations

    online video, appointment, choice

    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
    æłĸ
    -0.06
    ÑĢеменно
    -0.06
    %!
    -0.05
    奮
    -0.05
    mui
    -0.05
    åĩĿå¿ĥèģļåĬĽ
    -0.05
    IKE
    -0.05
    ilar
    -0.05
    åŀĥåľ¾
    -0.05
    ilian
    -0.05
    POSITIVE LOGITS
    å¤ĸéĺ´
    0.07
    èī³
    0.06
    æł¼è°ĥ
    0.06
     дели
    0.06
     comp
    0.06
    ä¸Ĭ岸
    0.06
    ynos
    0.05
     Blow
    0.05
    åľ¨çº¿ä¸Ĭ
    0.05
    èį¤
    0.05
    Activations Density 0.016%

    No Known Activations