© 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. 22261
    Prev
    Next
    INDEX
    Explanations

    politician, pen, fire, dog, weapons, cuisine

    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
    ogan
    -0.07
    εÏģι
    -0.06
    spacing
    -0.06
    acher
    -0.06
    ovor
    -0.06
    orda
    -0.06
    roz
    -0.06
    gede
    -0.06
     Pantal
    -0.06
    /original
    -0.06
    POSITIVE LOGITS
    ؤ
    0.06
    ipe
    0.05
    ugg
    0.05
    æĺ¯ä¸ĢåĪĩ
    0.05
    hubung
    0.04
    io
    0.04
    ç©¿è¡£æľį
    0.04
    åıĻ
    0.04
    ok
    0.04
    undert
    0.04
    Activations Density 0.009%

    No Known Activations