© 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. 16963
    Prev
    Next
    INDEX
    Explanations

    code structure and libraries

    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
    ç¬¬åĽĽæ¬¡
    -0.06
    éĩij鸡
    -0.05
    第ä¸ī次
    -0.05
    istu
    -0.05
    Įĵ
    -0.05
    erad
    -0.05
    Hashtable
    -0.05
    ÑĢÑĭн
    -0.05
    第äºĶ次
    -0.05
    ãĥŁãĥ³ãĤ°
    -0.05
    POSITIVE LOGITS
    веÑĤе
    0.06
    æĮĩæ´¾
    0.06
    çŃĸçķ¥
    0.05
     bluff
    0.05
     strategy
    0.05
     chế
    0.05
    èĥ½æ»¡è¶³
    0.05
    /simple
    0.05
     acting
    0.05
    enko
    0.05
    Activations Density 0.268%

    No Known Activations