© 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. 20118
    Prev
    Next
    INDEX
    Explanations

    abbreviations in parentheses

    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
    림
    -0.07
    Å¡ov
    -0.07
     Opin
    -0.07
    oux
    -0.07
    itionally
    -0.07
    bacher
    -0.07
    ."<
    -0.07
    对äºİè¿ĻäºĽ
    -0.07
    åĽ½å®¶åĴĮåľ°åĮºçļĦ
    -0.07
    éŃħ
    -0.06
    POSITIVE LOGITS
    ...
    0.05
    åĩºå¤Ħ
    0.05
    à¥į
    0.05
    ra
    0.05
    ä¸İ被
    0.05
    ç´¯
    0.05
    --
    0.04
    maybe
    0.04
    æµģ
    0.04
    åģĩå®ļ
    0.04
    Activations Density 0.039%

    No Known Activations