© 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. 7814
    Prev
    Next
    INDEX
    Explanations

    percentages and measurements

    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
    åħ¨éĥ¨
    -0.09
    9
    -0.08
    çĸĹ
    -0.08
    bes
    -0.08
    è·ijäºĨ
    -0.08
    sted
    -0.08
    apon
    -0.08
     Millennium
    -0.08
    8
    -0.08
     gang
    -0.08
    POSITIVE LOGITS
    ä¸ĥåħ«
    0.11
    äºĶåħŃ
    0.11
    åĽĽäºĶ
    0.11
    ä¸īåĽĽ
    0.10
    èĩ³ä¸Ĭ
    0.10
     prelim
    0.09
    两ä¸ī
    0.09
    åĪĨéĴŁå·¦åı³
    0.09
    æľ¬æĬ¥
    0.09
    èĽ¹
    0.08
    Activations Density 0.181%

    No Known Activations