© 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. 18312
    Prev
    Next
    INDEX
    Explanations

    apart from, other than

    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
    å°±åıªæľī
    -0.06
    icated
    -0.05
    æİĢèµ·äºĨ
    -0.05
     Wildcats
    -0.05
    ÑĩеÑĢед
    -0.05
    å°±è¶Ĭ
    -0.05
    alat
    -0.05
    å¤ĸç·ļ
    -0.05
     воÑģÑĮми
    -0.05
    hung
    -0.05
    POSITIVE LOGITS
    åĬŀçļĦ
    0.06
    zer
    0.06
    utz
    0.06
    ä½Ĩä¸įèĥ½
    0.05
    辦
    0.05
    ully
    0.05
    uent
    0.05
    eler
    0.05
     succesfully
    0.05
    uyu
    0.05
    Activations Density 0.013%

    No Known Activations