© 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. 20976
    Prev
    Next
    INDEX
    Explanations

    how to prevent

    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
    éĢģ
    -0.06
    çļĦ帮åĬ©
    -0.06
    æĬĽ
    -0.05
    hu
    -0.05
    iego
    -0.05
    æĶ¯
    -0.05
    çĥŃçĤ¹
    -0.05
    å¼ĺ
    -0.05
    ä¸ĬåĬł
    -0.05
    强
    -0.05
    POSITIVE LOGITS
    ãģ®ãģĭãĤĤ
    0.07
    oir
    0.06
     اÙĦÙħر
    0.06
    缨
    0.06
    делÑĮ
    0.06
    estiv
    0.06
    alom
    0.06
     intents
    0.06
    gli
    0.06
    解æ¶Ī
    0.05
    Activations Density 0.038%

    No Known Activations