© 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. 17063
    Prev
    Next
    INDEX
    Explanations

    surgical resection

    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
     dereg
    -0.06
    è±Ĩç±»
    -0.06
    èĪį
    -0.06
    lopen
    -0.05
    æĿŁ
    -0.05
     dinas
    -0.05
    æŃ¤é¡¹
    -0.05
     Oto
    -0.05
    亦çĦ¶
    -0.05
    央
    -0.05
    POSITIVE LOGITS
    ore
    0.06
    ade
    0.06
     warranted
    0.06
    åIJĮæŶè¦ģ
    0.05
     widers
    0.05
    eda
    0.05
     tháºŃp
    0.05
    å¾ĹæĿ¥
    0.05
     Litt
    0.05
    czy
    0.05
    Activations Density 0.159%

    No Known Activations