© 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. 17569
    Prev
    Next
    INDEX
    Explanations

    review problems

    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
    ible
    -0.06
    ébastien
    -0.06
    ç»ı审çIJĨæŁ¥æĺİ
    -0.06
    æį®ä»ĭç»į
    -0.06
    ÑĦеÑĢе
    -0.05
    人éĹ´
    -0.05
    å±ıæĿ±
    -0.05
    emus
    -0.05
    emarks
    -0.05
    <hr
    -0.05
    POSITIVE LOGITS
    aed
    0.06
    ç§į
    0.05
    aut
    0.05
    åįĥåŃĹ
    0.05
    endis
    0.05
    åīįåİ»
    0.05
    æ·±åĮĸ
    0.05
    Bre
    0.05
    ÑĢаÑĩи
    0.05
    ä¼°
    0.05
    Activations Density 0.009%

    No Known Activations