© 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. 19907
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    igin
    -0.06
    igas
    -0.06
    .ua
    -0.06
    kong
    -0.06
    igans
    -0.06
    é¡į
    -0.06
    zaÅĦ
    -0.06
    itti
    -0.06
     Aga
    -0.06
    æijĤ
    -0.06
    POSITIVE LOGITS
    éĺ³æĺİ
    0.05
    æľīä¸ĭåĪĹ
    0.05
    Ł
    0.05
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    0.05
    sid
    0.05
    obs
    0.05
    ucky
    0.04
    nowled
    0.04
    /
    0.04
     purpose
    0.04
    Activations Density 0.006%

    No Known Activations