© 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. 20376
    Prev
    Next
    INDEX
    Explanations

    put a lot

    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
    éĿ¢åIJij
    -0.09
    ius
    -0.08
    nos
    -0.07
     Trout
    -0.07
    å¨ģ
    -0.07
    sn
    -0.07
    oot
    -0.07
    shal
    -0.07
    defs
    -0.07
    بÙĩ
    -0.07
    POSITIVE LOGITS
    éĩįè§Ĩ
    0.14
    çľĭéĩį
    0.12
    é«ĺ度éĩįè§Ĩ
    0.10
    强è°ĥ
    0.10
    解读
    0.10
    说çļĦè¯Ŀ
    0.10
    éĤ¸
    0.10
    说èĩªå·±
    0.09
    åĺ´åĶĩ
    0.09
    饼
    0.09
    Activations Density 0.020%

    No Known Activations