© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12002
    Prev
    Next
    INDEX
    Explanations

    NOT FOR PUBLICATION OR PRECEDENTIAL

    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
    西äºļ
    -0.09
    ä¸įä¸ĭ
    -0.09
    ä¸įäºĨ
    -0.08
    æī¹
    -0.08
    ober
    -0.08
    没éĹ®é¢ĺ
    -0.08
    ä¾¿å®ľ
    -0.08
    æī¹å¤į
    -0.08
    禧
    -0.08
    æħ·æħ¨
    -0.07
    POSITIVE LOGITS
    porn
    0.10
    .Bus
    0.10
    åıªæĺ¯ä¸Ģ个
    0.10
    WORDS
    0.10
    FOUND
    0.10
    稳
    0.10
    è´ŁåĢº
    0.09
    åĩºçīĪ
    0.09
    ammer
    0.09
    ÙĬدÙĬ
    0.09
    Activations Density 0.171%

    No Known Activations