© 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. 17408
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
    åı¦ä¸ĢåįĬ
    -0.06
    owed
    -0.06
    ãģijãĤĭãģ¨
    -0.06
    ERIA
    -0.06
    å®£ä¼łè´¯å½»
    -0.06
    éĤ£éģĵ
    -0.06
    descr
    -0.06
    herits
    -0.06
    ä¸ĭè»Ĭ
    -0.05
    kenal
    -0.05
    POSITIVE LOGITS
    ilter
    0.05
     \""
    0.05
     inch
    0.05
    oard
    0.05
     past
    0.05
    ?url
    0.05
    даÑĤа
    0.05
     int
    0.04
     Couch
    0.04
    æĶ¾ç½®åľ¨
    0.04
    Activations Density 0.083%

    No Known Activations