© 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. 26137
    Prev
    Next
    INDEX
    Explanations

    groove or grove

    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
    ãģĦãĤĭ
    -0.11
    ç¾¹
    -0.09
    road
    -0.09
    ped
    -0.09
    noon
    -0.09
    çĦ¶æĺ¯
    -0.09
    aul
    -0.09
    ohn
    -0.09
    ape
    -0.09
    æºī
    -0.09
    POSITIVE LOGITS
    ç²Ŀ
    0.10
    utors
    0.10
    hound
    0.10
    侧ç»ĵæŀĦæĢ§
    0.10
    ulia
    0.09
    å£ij
    0.09
    bsite
    0.09
    phis
    0.09
    esh
    0.09
    çħ
    0.09
    Activations Density 0.015%

    No Known Activations