© 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. 17446
    Prev
    Next
    INDEX
    Explanations

    my mind

    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
    راÙħ
    -0.06
    ä¹ĭæĺŁ
    -0.05
     suj
    -0.05
    æľ¬åįıè®®
    -0.05
     everyone
    -0.05
    æľīçĶŁ
    -0.05
    оÑģÑĥ
    -0.05
    ëĤĺë§Ī
    -0.05
     everybody
    -0.05
    éĩijçİī
    -0.05
    POSITIVE LOGITS
    lett
    0.06
    åĭ¢
    0.06
    pard
    0.06
    alma
    0.06
    жина
    0.06
    odate
    0.06
    perk
    0.06
    åĬ¿
    0.06
    /do
    0.06
    æ±Ĥ人
    0.06
    Activations Density 0.001%

    No Known Activations