© 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. 19035
    Prev
    Next
    INDEX
    Explanations

    1

    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
    udan
    -0.07
    lice
    -0.06
    è¿Ļæł·åı¯ä»¥
    -0.06
     provato
    -0.06
    åĦ¿
    -0.06
    uda
    -0.06
    autical
    -0.06
    мееÑĤÑģÑı
    -0.06
    ude
    -0.06
     sustained
    -0.06
    POSITIVE LOGITS
    è·Ł
    0.05
    yg
    0.05
     vom
    0.05
    )?$
    0.05
    äºĨåij¢
    0.05
     ard
    0.05
     ab
    0.05
    ìĸ´ëĵľ
    0.05
    çĬĢ
    0.04
    à¸ĺิ
    0.04
    Activations Density 0.111%

    No Known Activations