© 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. 2785
    Prev
    Next
    INDEX
    Explanations

    space exploration and earth orbit

    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
    prime
    -0.11
    çĻ½æĸij
    -0.10
    æĦıåIJij
    -0.10
    èijŃ
    -0.09
    éĩįæķ´
    -0.09
    çĸĥ
    -0.09
    æĪĹ
    -0.09
    ä¸ĬéŨ
    -0.09
    æģº
    -0.09
    å§Ĺ
    -0.09
    POSITIVE LOGITS
     space
    0.10
    浩
    0.10
     окол
    0.10
    iek
    0.09
    space
    0.09
    closure
    0.09
    æ®Ĭ
    0.09
    究竣
    0.09
    çķĻä½ı
    0.09
    æĺŁç©º
    0.09
    Activations Density 0.030%

    No Known Activations