© 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. 20593
    Prev
    Next
    INDEX
    Explanations

    git diffs and file changes

    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
     sucedido
    -0.06
    çĶĺ
    -0.06
    thic
    -0.06
    ÑİÑĢ
    -0.06
     hustle
    -0.06
    Ïģεί
    -0.06
    erv
    -0.06
    CRET
    -0.06
     formulated
    -0.06
    ful
    -0.06
    POSITIVE LOGITS
     Change
    0.06
     changes
    0.06
    åıĺæĽ´åīį
    0.06
     Changes
    0.06
    ote
    0.06
     diffs
    0.06
    æŧ
    0.06
    åıĺæĽ´
    0.06
     change
    0.06
    åıĺåĮĸ
    0.06
    Activations Density 0.152%

    No Known Activations