© 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. 22303
    Prev
    Next
    INDEX
    Explanations

    research and finding

    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
    lesh
    -0.10
    佺
    -0.10
    æĸĩåĮĸä¼łæĴŃ
    -0.09
     phil
    -0.08
    ony
    -0.08
    åħ¸
    -0.08
    Ware
    -0.08
    åįłæį®äºĨ
    -0.08
    Land
    -0.08
    Ñįм
    -0.08
    POSITIVE LOGITS
    çłĶ究
    0.16
    çłĶ究æĪIJæŀľ
    0.13
    çłĶåıijä¸Ńå¿ĥ
    0.11
    çłĶåıij
    0.11
    çłĶ
    0.10
    çłĶ究表æĺİ
    0.10
     research
    0.10
    å¥ĩ迹
    0.10
    çłĶ究åijĺ
    0.10
    çłĶåĪ¶
    0.10
    Activations Density 0.115%

    No Known Activations