© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10548
    Prev
    Next
    INDEX
    Explanations

    film, theatre, and art production roles

    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
    æŁĶåĴĮ
    -0.09
    cha
    -0.09
    æ®ĸ
    -0.09
    èĬ³é¦Ļ
    -0.09
    åŁºåĩĨ
    -0.09
    erot
    -0.09
    æŁĶ
    -0.09
    æĥĭ
    -0.09
    è¹²
    -0.09
    nest
    -0.08
    POSITIVE LOGITS
    åī§
    0.15
    èĪŀåı°
    0.15
    æ¼Ķåijĺ
    0.15
    æ¼Ķ
    0.15
    主æ¼Ķ
    0.15
     actors
    0.15
    åī§æĥħ
    0.15
    åī§æľ¬
    0.14
    .Actor
    0.14
    åľºæĻ¯
    0.14
    Activations Density 0.122%

    No Known Activations