© 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. 20103
    Prev
    Next
    INDEX
    Explanations

    describing or labeling parts

    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
    orp
    -0.06
     âģ
    -0.06
    å®¡æł¸åIJİ
    -0.06
    епен
    -0.06
    æĹłæķħ
    -0.06
    æľīæĿ¡ä»¶çļĦ
    -0.06
    åIJĦéĥ¨éŨ
    -0.05
    볤
    -0.05
    æ¯ħ
    -0.05
    åįģ
    -0.05
    POSITIVE LOGITS
    abouts
    0.06
    warts
    0.06
    asil
    0.06
    å°ijéĩıçļĦ
    0.05
    oder
    0.05
    åĪĽæĬķ
    0.05
     foresee
    0.05
    ergus
    0.05
    isit
    0.05
    atu
    0.05
    Activations Density 0.001%

    No Known Activations