© 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. 51333
    Prev
    Next
    INDEX
    Explanations

    Bowie, Boise, Wichita, Bose

    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
    uck
    -0.09
    éģŃ
    -0.09
    èĤĺ
    -0.09
    èľĵ
    -0.08
    tings
    -0.08
    ãģªãģĭ
    -0.08
    缸åıį
    -0.08
    举é£İ
    -0.08
    PRESSION
    -0.08
     flaming
    -0.08
    POSITIVE LOGITS
    ä¹İ
    0.11
    婺
    0.10
    åıĪ好
    0.09
     Beckham
    0.09
    åĤ¨éĩı
    0.09
    æĹ¥æĬ¥è®°èĢħ
    0.09
    otle
    0.09
    çĴľ
    0.09
    æĪijåĸľæ¬¢
    0.09
    efore
    0.08
    Activations Density 0.003%

    No Known Activations