© 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. 17194
    Prev
    Next
    INDEX
    Explanations

    output and print code

    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
    Ïģεί
    -0.06
    inker
    -0.06
    åĬŁå¾·
    -0.06
     thẩm
    -0.06
    Ñĩо
    -0.05
    neys
    -0.05
     Stretch
    -0.05
     ASSIGN
    -0.05
     Incre
    -0.05
     Peny
    -0.05
    POSITIVE LOGITS
    ohan
    0.06
    phan
    0.05
    ÑĨ
    0.05
    orex
    0.05
    åıĹ欢è¿İçļĦ
    0.05
    xious
    0.05
    orget
    0.05
    gue
    0.05
    ган
    0.05
    è²Į
    0.05
    Activations Density 0.022%

    No Known Activations