© 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. 27563
    Prev
    Next
    INDEX
    Explanations

    gratitude and thanks

    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
    çĤķ
    -0.10
    .Meta
    -0.09
    ä»ĬåIJİ
    -0.09
    è¿·ä¿¡
    -0.09
    инг
    -0.09
    æľĢå¿«
    -0.09
    èĮ§
    -0.09
    rite
    -0.09
    åIJĥäºı
    -0.09
    å®ĺåı¸
    -0.09
    POSITIVE LOGITS
    æ¬
    0.09
    æ¶ķ
    0.09
     Led
    0.09
    ully
    0.09
    æĦŁè°¢
    0.08
    éªĭ
    0.08
    Ñģан
    0.08
    æĥ¬
    0.08
    ارÙĬ
    0.08
    ably
    0.08
    Activations Density 0.045%

    No Known Activations