© 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. 21204
    Prev
    Next
    INDEX
    Explanations

    either ... or

    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
    ple
    -0.06
     ref
    -0.06
    rey
    -0.05
    åĢ¼
    -0.05
    fore
    -0.05
     hint
    -0.05
    ÉĻrÉĻ
    -0.04
    é¦
    -0.04
    just
    -0.04
    zer
    -0.04
    POSITIVE LOGITS
    ekt
    0.06
    esimo
    0.06
    -peer
    0.06
    лио
    0.06
    éķ¿æľŁåĿļæĮģ
    0.06
    ektor
    0.06
    ancock
    0.06
    åıĺæĽ´ä¿¡æģ¯
    0.06
    taal
    0.06
    åİħéķ¿
    0.06
    Activations Density 0.001%

    No Known Activations