© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26160
    Prev
    Next
    INDEX
    Explanations

    energy states

    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
    Negative Logits
    toa
    -0.10
    ordan
    -0.09
    æķ£
    -0.09
     surrounds
    -0.09
    建åĨĽ
    -0.09
    ãĥķãĥĪ
    -0.09
    æ¥Ń
    -0.09
     ÙĦÙĬست
    -0.09
    гÑĥ
    -0.09
    ãģĹãģ¦ãģįãģŁ
    -0.09
    POSITIVE LOGITS
    çĬ¶æĢģ
    0.14
     state
    0.12
     states
    0.12
    çĬ¶æĢģä¸ĭ
    0.12
     STATES
    0.11
    çĭĢæħĭ
    0.11
     ÑģоÑģÑĤоÑıнии
    0.10
     lif
    0.10
    é«ĺä½İ
    0.10
    çļĦçĬ¶æĢģ
    0.09
    Activations Density 0.220%

    No Known Activations