© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20770
    Prev
    Next
    INDEX
    Explanations

    also + verb

    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
    å°¤åħ¶
    -0.09
     especially
    -0.09
    apan
    -0.08
    ÑģÑĤÑĢел
    -0.08
     even
    -0.08
    çħ§
    -0.08
    æĹ¢
    -0.08
     certainly
    -0.08
    amas
    -0.07
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.07
    POSITIVE LOGITS
    åħ¶ä»ĸ
    0.18
    åħ¶ä»ĸçļĦ
    0.17
    åĪ«çļĦ
    0.17
    åħ¶å®ĥéĹ®é¢ĺ
    0.16
    åħ¶å®ĥ
    0.14
    åı¦å¤ĸ
    0.14
     other
    0.13
    è¿ĺåĮħæĭ¬
    0.13
     outros
    0.13
     дÑĢÑĥгиÑħ
    0.13
    Activations Density 0.143%

    No Known Activations