© 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. 20204
    Prev
    Next
    INDEX
    Explanations

    eagle Sing

    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
    å¥ĩå¦Ļ
    -0.11
    hop
    -0.10
    .addListener
    -0.09
     Doll
    -0.09
    äºĴèģĶäºĴéĢļ
    -0.09
    stück
    -0.09
    ä¸įåı¯æĢĿè®®
    -0.09
    çĿ¡åīį
    -0.09
    åĿĬ
    -0.08
    èĪĮ
    -0.08
    POSITIVE LOGITS
    翱
    0.11
    é«ĺé¢Ŀ
    0.10
    idan
    0.09
    é«ĺä»·
    0.09
    èµ·é£ŀ
    0.09
    éªĸ
    0.09
    ÑħваÑĤ
    0.09
    ä¹Į
    0.09
    åĩĨ
    0.08
    è§Ī
    0.08
    Activations Density 0.036%

    No Known Activations