© 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. 51066
    Prev
    Next
    INDEX
    Explanations

    outscored opponents by

    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
    åĽ½å®ī
    -0.10
    åĬŀåħ¬æ¥¼
    -0.10
    åħ¬åı¸å°Ĩ
    -0.10
    rowable
    -0.09
    æĿĢ
    -0.09
    marks
    -0.09
    æ´¾éģ£
    -0.09
    èĶº
    -0.09
    ongs
    -0.09
    æķıæį·
    -0.09
    POSITIVE LOGITS
    acco
    0.09
    wa
    0.08
    宾
    0.08
    Appe
    0.08
    æ¼ı
    0.08
    éĹ¹
    0.08
     leak
    0.08
    èĢģåĮĸ
    0.08
    endency
    0.08
    ENSE
    0.08
    Activations Density 0.006%

    No Known Activations