© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9509
    Prev
    Next
    INDEX
    Explanations

    deserve or earned

    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
    licity
    -0.09
    ç«¥
    -0.09
    cko
    -0.09
    çĶĺ
    -0.08
    è¿Ń
    -0.08
     SPELL
    -0.08
    ä¸įå®ļ
    -0.08
    igon
    -0.08
    æĢ»å±Ģ
    -0.08
    åĽŀåIJĪ
    -0.08
    POSITIVE LOGITS
    çģŃ亡
    0.09
    apos
    0.09
    æĬ¥åºŁ
    0.09
    Ñīа
    0.09
    è¡Į使
    0.09
    è¿Ļä¹Īåģļ
    0.08
     Pose
    0.08
    æݥ触åĪ°
    0.08
    happy
    0.08
    /right
    0.08
    Activations Density 0.018%

    No Known Activations