© 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. 17577
    Prev
    Next
    INDEX
    Explanations

    . and for

    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
    onet
    -0.06
    æĹ¢
    -0.06
    æīĢä½ľ
    -0.05
    оне
    -0.05
    å¤ļäºİ
    -0.05
    æĹ¢ä¸į
    -0.05
     bes
    -0.05
     fert
    -0.05
     coll
    -0.05
    àµĥ
    -0.05
    POSITIVE LOGITS
    –and
    0.06
    cheid
    0.06
    trin
    0.06
    wis
    0.06
    athy
    0.06
    anca
    0.05
    alez
    0.05
    versa
    0.05
    è¿Ļæīįæĺ¯
    0.05
    isque
    0.05
    Activations Density 0.109%

    No Known Activations