© 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. 18718
    Prev
    Next
    INDEX
    Explanations

    loop through or iterate over

    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
     per
    -0.06
    mb
    -0.05
    客
    -0.05
     exp
    -0.05
    apr
    -0.05
    ä¼´ä¾£
    -0.05
     particularly
    -0.04
    åIJİçļĦ
    -0.04
    atore
    -0.04
    ä¸ĭå±±
    -0.04
    POSITIVE LOGITS
    /name
    0.06
     saz
    0.06
    nez
    0.06
    )>>
    0.06
    æĸ°äº¬
    0.06
    ä¸ĢåĪĻ
    0.06
     lutka
    0.06
     rekan
    0.06
    bild
    0.06
    isola
    0.06
    Activations Density 0.002%

    No Known Activations