© 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. 7510
    Prev
    Next
    INDEX
    Explanations

    location and facilities

    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
    åĵ
    -0.08
    橱
    -0.08
    YRO
    -0.08
    åŃ¦ä¹łæĪIJ绩
    -0.08
    æĬ¥è®°èĢħ
    -0.08
    Inspectable
    -0.08
    åŀ¢
    -0.08
    è¸ŀ
    -0.08
    ila
    -0.08
     Bend
    -0.08
    POSITIVE LOGITS
    è¿ĻçĤ¹
    0.11
    触åıĬ
    0.09
    è¿Ļ家
    0.09
    ç»Ĩå¾®
    0.09
    ä¸Ģ家
    0.08
    æĹłçº¿çĶµ
    0.08
    linky
    0.08
    -reaching
    0.08
    çªĦ
    0.08
    aghan
    0.08
    Activations Density 0.287%

    No Known Activations