© 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. 19077
    Prev
    Next
    INDEX
    Explanations

    code variable declarations

    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
    antin
    -0.06
    venta
    -0.06
    *”,
    -0.06
     pains
    -0.06
    arder
    -0.06
    ):-
    -0.05
    åģ¶
    -0.05
    *”.
    -0.05
    sher
    -0.05
    é¢ł
    -0.05
    POSITIVE LOGITS
    ç¼ĸè¾ijäºİ
    0.06
    rohr
    0.05
     ÑĢоÑĤ
    0.05
    çī¹æĸ¯
    0.05
    çıĤ
    0.05
    åı¯æĥ³
    0.05
    ä½łçŁ¥éģĵ
    0.05
    ç«£
    0.05
     consensus
    0.05
     lest
    0.05
    Activations Density 0.058%

    No Known Activations