© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20959
    Prev
    Next
    INDEX
    Explanations

    depends on

    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
    æĪĸå¤ļ个
    -0.06
    à¸ĺุ
    -0.06
    żyÄĩ
    -0.05
     Satisfaction
    -0.05
     pant
    -0.05
    缸åħ³ä¸ĵä¸ļ
    -0.05
    uit
    -0.05
     satisfaction
    -0.05
    æĶ¶æį®
    -0.04
    дон
    -0.04
    POSITIVE LOGITS
    Depending
    0.07
     depending
    0.07
    åħĭ森
    0.07
     Depending
    0.07
     varying
    0.06
     differing
    0.06
     بستÙĩ
    0.06
     differ
    0.06
     varies
    0.06
    edakan
    0.06
    Activations Density 0.104%

    No Known Activations