© 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. 62257
    Prev
    Next
    INDEX
    Explanations

    email addresses

    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
    èĤĭ
    -0.09
    åħ¨éķĩ
    -0.09
     radiant
    -0.08
    楼ä¸Ĭ
    -0.08
    åĽ°
    -0.08
    楼ä¸ĭ
    -0.08
    è¢«åĽ°
    -0.08
    èħĬ
    -0.08
    ä»ĭ
    -0.08
     Meredith
    -0.08
    POSITIVE LOGITS
    éªħ
    0.10
    æľ¬çĿĢ
    0.10
    éĵľ
    0.09
    éķĽ
    0.09
    xbe
    0.09
    ä¸į让
    0.09
     Bhar
    0.08
    强çĥĪ
    0.08
    ç§ģ人
    0.08
    è¶³å¤ŁçļĦ
    0.08
    Activations Density 0.010%

    No Known Activations