© 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. 20367
    Prev
    Next
    INDEX
    Explanations

    locations and dates

    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
    åģ
    -0.06
    à¹Ģà¸Ķียว
    -0.05
    æ½ľ
    -0.05
    ķ
    -0.05
    ä¸ĥä¸Ģ
    -0.05
    åĶ¯ä¸Ģ
    -0.05
    表éĿ¢ä¸Ĭ
    -0.05
    å»¶è¿Ł
    -0.05
    ä¿ĿçķĻ
    -0.05
    æµ·çĩķ
    -0.05
    POSITIVE LOGITS
    umper
    0.06
    —but
    0.06
    alk
    0.06
    .${
    0.06
     perspec
    0.06
     استث
    0.06
     finals
    0.06
    itorios
    0.06
    —who
    0.06
    yla
    0.06
    Activations Density 0.048%

    No Known Activations