© 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. 6070
    Prev
    Next
    INDEX
    Explanations

    business and startup concepts

    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
    æĵİ
    -0.09
     ProgressBar
    -0.09
    ymax
    -0.08
    angs
    -0.08
    çĻ¾ç§ij
    -0.08
    ibo
    -0.08
    ayers
    -0.08
    (sq
    -0.08
     sund
    -0.08
    ãĥĹãĥ©ãĤ¹
    -0.08
    POSITIVE LOGITS
    åīµæ¥Ń
    0.10
    å»ĵ
    0.10
    åĪĽä¸ļ
    0.10
    çºłæŃ£
    0.09
    pitch
    0.09
    æī¶
    0.09
    åĪĽä¸ļèĢħ
    0.08
    æ®ī
    0.08
    æŦ
    0.08
     boarding
    0.08
    Activations Density 0.069%

    No Known Activations