© 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. 17331
    Prev
    Next
    INDEX
    Explanations

    when you would

    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
     nonetheless
    -0.06
    ä¸Ģæĸij
    -0.06
     aber
    -0.06
     nevertheless
    -0.06
     however
    -0.05
    ordia
    -0.05
     jedoch
    -0.05
    árs
    -0.05
    åį´è¢«
    -0.05
    并被
    -0.05
    POSITIVE LOGITS
    å¥ĩ迹
    0.06
    ãĢģ“
    0.06
    rod
    0.06
    /or
    0.06
     ytter
    0.06
     proprio
    0.06
    werpen
    0.05
    âĢķâĢķâĢķâĢķ
    0.05
    unc
    0.05
    ri
    0.05
    Activations Density 0.074%

    No Known Activations