© 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. 36559
    Prev
    Next
    INDEX
    Explanations

    can use

    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
    esson
    -0.10
    ussen
    -0.10
    åħ¬åħ±æľįåĬ¡
    -0.09
    æĸŃ
    -0.08
    çľĭ好
    -0.08
    amon
    -0.08
    éľĩèį¡
    -0.08
    好å¥ĩ
    -0.08
    hé
    -0.08
    ogne
    -0.08
    POSITIVE LOGITS
    æģ°æģ°
    0.10
    ä¾ĿçĦ¶
    0.10
    å±ħçĦ¶
    0.10
    æ³ģ
    0.09
    èĢĮåıĪ
    0.09
    æ¯ı个人çļĦ
    0.09
    åı¯ä»¥ä½¿
    0.09
     ÑĤоже
    0.09
    æģ¤
    0.09
    EA
    0.08
    Activations Density 0.053%

    No Known Activations