© 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. 18427
    Prev
    Next
    INDEX
    Explanations

    command above; see

    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
     gentil
    -0.06
    çĸijéļ¾
    -0.05
    å¤Ħéķ¿
    -0.05
    éĹ®é¢ĺçļĦèĥ½åĬĽ
    -0.05
    ellow
    -0.05
    帮
    -0.05
    ohl
    -0.05
    æ¡ĪçĶ±
    -0.05
     inherit
    -0.05
    æľĭ
    -0.05
    POSITIVE LOGITS
    weiler
    0.06
    rän
    0.06
    igin
    0.06
    ertet
    0.06
    óg
    0.06
    åŃļ
    0.06
    unci
    0.06
     ÙħÙĪاÙĤ
    0.06
    uncio
    0.05
    æ®Ĭä¸įçŁ¥
    0.05
    Activations Density 0.001%

    No Known Activations