© 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. 20370
    Prev
    Next
    INDEX
    Explanations

    considered or regarded as

    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
    plib
    -0.09
     Insp
    -0.08
    累累
    -0.08
    è¦ģæľī
    -0.08
    zie
    -0.08
    ional
    -0.08
    scale
    -0.08
    åħ¼
    -0.08
    æīij
    -0.08
     плаÑģÑĤ
    -0.08
    POSITIVE LOGITS
    被认为æĺ¯
    0.18
    被èªī为
    0.16
    被è§Ĩ为
    0.16
    被认为
    0.15
    被èªī
    0.15
    åħ¬è®¤
    0.14
    åħ¬è®¤çļĦ
    0.14
    è§Ĩ为
    0.14
    éĥ½è®¤ä¸º
    0.14
     ÑģÑĩиÑĤ
    0.13
    Activations Density 0.118%

    No Known Activations