© 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. 4370
    Prev
    Next
    INDEX
    Explanations

    contact information or availability

    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
    æĭ¢
    -0.08
    è§ī
    -0.08
    åĬłä¸Ĭ
    -0.08
    交éĶĻ
    -0.08
    解èĦ±
    -0.08
    Pull
    -0.08
    odo
    -0.08
     Val
    -0.08
    æ¯ķç«Ł
    -0.08
     Bat
    -0.08
    POSITIVE LOGITS
    èģĶç³»æĸ¹å¼ı
    0.12
    åħ®
    0.11
    èģĶç³»çĶµè¯Ŀ
    0.11
    âĺİ
    0.11
    çĶµè¯Ŀ
    0.10
    宪
    0.10
    èģĶç³»
    0.09
    contact
    0.09
    æĦıè§ģ
    0.09
    ðŁĵŀ
    0.09
    Activations Density 0.006%

    No Known Activations