© 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. 16934
    Prev
    Next
    INDEX
    Explanations

    command-line arguments and code structure

    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
    路交åıīåı£
    -0.06
    etem
    -0.06
    åħ¶ä»ĸ人
    -0.06
    åĥļ
    -0.06
    ";}
    -0.06
     lainnya
    -0.06
    uvo
    -0.06
    añ
    -0.06
    è¿ĶåĽŀ顶éĥ¨
    -0.06
    åħ¶ä»ĸåĽ½å®¶
    -0.06
    POSITIVE LOGITS
    imentos
    0.05
    มà¸Ļ
    0.05
    vál
    0.05
    engan
    0.05
     Mend
    0.05
    ENSE
    0.05
    åıĺéĢģ
    0.05
    ä¸įéĢļ
    0.04
    ç»´äºļ
    0.04
    ä¸Ĭæĸ¹çļĦ
    0.04
    Activations Density 0.010%

    No Known Activations