© 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. 20451
    Prev
    Next
    INDEX
    Explanations

    URL and file paths

    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
    éĥ¨éķ¿
    -0.07
    ries
    -0.06
    ãĤ¤ãĥĪ
    -0.06
    agus
    -0.06
    isd
    -0.06
    åħ«éĥ¨
    -0.06
    ä¸įåĪĨ
    -0.06
    éķ¿å¹´
    -0.06
    èIJ½ä¸ĭ
    -0.06
     incumbent
    -0.06
    POSITIVE LOGITS
    æĮĩäºĨæĮĩ
    0.06
     rout
    0.06
     mot
    0.06
    ÙĦاج
    0.06
    acker
    0.05
    æľĢåĪĿçļĦ
    0.05
    æĵįä½ľæµģç¨ĭ
    0.05
    åıªæĺ¯ä¸Ģ个
    0.05
    ÐłÐIJÐĿ
    0.05
    æ¯ĶæĭŁ
    0.05
    Activations Density 0.009%

    No Known Activations