© 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. 60582
    Prev
    Next
    INDEX
    Explanations

    market size and demand

    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
    wish
    -0.08
    å·¢
    -0.08
    ä»°
    -0.08
    åĪ°è´¦
    -0.08
    ä¸ĢäºĽ
    -0.08
    åı£ä¸Ń
    -0.08
    elves
    -0.08
    lernen
    -0.07
    çĻ¾ç§ij
    -0.07
     Sachs
    -0.07
    POSITIVE LOGITS
    å¸ĤåľºéľĢæ±Ĥ
    0.26
    å¸Ĥåľºè§Ħ模
    0.18
    å¸Ĥåľº
    0.17
    å¸ĤåľºçļĦ
    0.17
    客æĪ·éľĢæ±Ĥ
    0.16
     market
    0.16
    å¸Ĥåľºä¸Ĭ
    0.15
    éľĢæ±Ĥ
    0.15
     demand
    0.14
    å¸Ĥåł´
    0.14
    Activations Density 0.083%

    No Known Activations