© 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. 18431
    Prev
    Next
    INDEX
    Explanations

    architectural forms and objects

    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
    æīįèĥ½
    -0.05
    ä¸ĢæŶ
    -0.05
    ãģ¾ãģŁ
    -0.05
    ima
    -0.05
     (
    -0.05
    壮
    -0.05
    elar
    -0.05
     V
    -0.05
    —not
    -0.05
    hv
    -0.05
    POSITIVE LOGITS
    okol
    0.06
    ç¨ĭ
    0.06
     prel
    0.06
    schul
    0.06
    èvres
    0.06
    ul
    0.06
    apres
    0.06
     جÙĩ
    0.05
     lige
    0.05
    è¿ĻäºĽåľ°æĸ¹
    0.05
    Activations Density 0.106%

    No Known Activations