© 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. 19909
    Prev
    Next
    INDEX
    Explanations

    **throughout**

    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
     at
    -0.06
    -0.05
     absol
    -0.05
    vis
    -0.05
    ä¹Łç½¢
    -0.05
     Compilation
    -0.05
    rend
    -0.05
    ä¿®
    -0.05
    est
    -0.05
     Bestand
    -0.05
    POSITIVE LOGITS
     hinweg
    0.07
     Entire
    0.07
     entire
    0.06
    ä¸Ģéģį
    0.06
     entusias
    0.06
     cuesta
    0.06
    æŃ£åıį
    0.06
    æķ´ä¸ª
    0.06
    éĻ£
    0.06
     hele
    0.06
    Activations Density 0.085%

    No Known Activations