© 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. 21287
    Prev
    Next
    INDEX
    Explanations

    code formatting

    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
    ìĿ´ìĸ´
    -0.05
    以为æĺ¯
    -0.05
    æ±Ĥæĺ¯
    -0.05
    ulich
    -0.05
    øy
    -0.05
    ischt
    -0.05
     myster
    -0.05
    isch
    -0.05
    ly
    -0.05
    ÑĢий
    -0.05
    POSITIVE LOGITS
    quee
    0.05
    yt
    0.05
    abil
    0.05
    临
    0.05
    çĤ¹åIJİ
    0.05
    irt
    0.05
    appar
    0.05
    atment
    0.05
    ä¸İæľ¬
    0.05
    itional
    0.05
    Activations Density 0.004%

    No Known Activations