© 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. 22658
    Prev
    Next
    INDEX
    Explanations

    driving license category B, C, 6

    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
    turtle
    -0.09
    HELL
    -0.09
    æĤ£
    -0.09
    çŃīæĥħåĨµ
    -0.09
    txn
    -0.09
    apus
    -0.08
    çħŀ
    -0.08
    å¥ĹæĪ¿
    -0.08
    åī¥
    -0.08
     Mull
    -0.08
    POSITIVE LOGITS
    驾çħ§
    0.10
    驾驶è¯ģ
    0.10
    æĹłæīĢ
    0.10
    åĸ·
    0.10
    -license
    0.09
    æħij
    0.09
    æĮģæľīçļĦ
    0.09
     licence
    0.09
    åŁ¹è®ŃçıŃ
    0.09
    æĬ¥
    0.09
    Activations Density 0.040%

    No Known Activations