© 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. 20088
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    urada
    -0.06
    idon
    -0.05
    ünden
    -0.05
    tus
    -0.05
    èĥĮä¸Ĭ
    -0.05
    ä¸İåīį
    -0.05
    åģĩåĨĴ
    -0.05
    arit
    -0.05
    hs
    -0.05
     Rez
    -0.05
    POSITIVE LOGITS
     role
    0.06
    rop
    0.06
    é¡Į
    0.05
    cam
    0.05
    åħ·ä½ĵæŶéĹ´
    0.05
    licherweise
    0.05
    èĢĮèµ°
    0.05
    yp
    0.05
    Role
    0.05
    顺
    0.05
    Activations Density 0.000%

    No Known Activations