© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 55446
    Prev
    Next
    INDEX
    Explanations

    spontaneously resolve or close

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    lish
    -0.10
    ä¸įæĺĵ
    -0.09
    åŃľ
    -0.08
    樱
    -0.08
    èµ·é£ŀ
    -0.08
    bach
    -0.08
    Compat
    -0.08
    roke
    -0.08
    kok
    -0.08
    ç¦ħ
    -0.08
    POSITIVE LOGITS
    æģ¢å¤įæŃ£å¸¸
    0.14
    å¾Īå¿«å°±
    0.13
    éļıçĿĢæŶéĹ´
    0.13
     Ñģамо
    0.12
    æģ¢å¤į
    0.12
    è¿ĩäºĨ
    0.12
    æģ¢
    0.11
    å¾Īå¿«
    0.11
    èĩªçĦ¶
    0.11
     eventually
    0.10
    Activations Density 0.112%

    No Known Activations