© 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. 16844
    Prev
    Next
    INDEX
    Explanations

    another followed by a noun/adjective

    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
    halb
    -0.10
    ØŃد
    -0.09
    -0.09
    ert
    -0.09
    ä¸ĢæŦ
    -0.09
     same
    -0.09
     Omn
    -0.08
    ×ķת
    -0.08
    lam
    -0.08
    漫
    -0.08
    POSITIVE LOGITS
    ãģĻãģIJ
    0.12
    -than
    0.11
    人éĥ½
    0.11
    ãģĤãĤĭç¨ĭ度
    0.11
    -generation
    0.11
    /new
    0.10
    _than
    0.10
    ãģĹãģ¦ãĤĤ
    0.10
    æ´ĭæ´ĭ
    0.10
    ä¸Ģå±Ĥ
    0.10
    Activations Density 0.033%

    No Known Activations