© 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. 20703
    Prev
    Next
    INDEX
    Explanations

    I 'm

    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
    arg
    -0.05
    isel
    -0.05
    /]
    -0.05
    éĢļè¿ĩè¿ĻäºĽ
    -0.05
     embedded
    -0.05
    erecht
    -0.05
     Asc
    -0.05
    æĥħ人
    -0.05
    ARG
    -0.05
    iak
    -0.05
    POSITIVE LOGITS
    åı¯ä¾Ŀ
    0.07
    aimer
    0.07
    çİīå±±
    0.06
    atis
    0.06
    éĿĵ
    0.06
    inus
    0.05
    ieh
    0.05
    迪æĸ¯
    0.05
     yếu
    0.05
    currently
    0.05
    Activations Density 0.007%

    No Known Activations