© 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. 52903
    Prev
    Next
    INDEX
    Explanations

    kayak tour

    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
    edImage
    -0.12
    éľŃ
    -0.10
    æĦŁè§īèĩªå·±
    -0.10
    åIJĪãģĦ
    -0.10
    è¦ģ好好
    -0.10
    å¿Į
    -0.09
    è·ŁæĪij说
    -0.09
    饼
    -0.09
    BACK
    -0.09
    eds
    -0.09
    POSITIVE LOGITS
    æ¼Ĥæµģ
    0.09
    лик
    0.09
    onet
    0.09
    å¼Ģå°ģ
    0.09
    ÑĢоÑĪ
    0.08
    åıĸè¯ģ
    0.08
    èĪ¬
    0.08
    oola
    0.08
    ãĤ®ãĥ£
    0.08
    athers
    0.08
    Activations Density 0.005%

    No Known Activations