© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31202
    Prev
    Next
    INDEX
    Explanations

    county names

    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
    æĮĤåı·
    -0.09
    idy
    -0.09
    issy
    -0.08
     Pitt
    -0.08
     invol
    -0.08
    åĽŀé¦Ī
    -0.08
    å°ıå§IJå§IJ
    -0.08
     retiring
    -0.07
    çīĩåŃIJ
    -0.07
    驾车
    -0.07
    POSITIVE LOGITS
    .dispatcher
    0.10
    för
    0.10
    æī¯
    0.09
    _bonus
    0.09
    orton
    0.09
    磾
    0.09
    agus
    0.09
    ania
    0.09
    临
    0.09
    aga
    0.09
    Activations Density 0.064%

    No Known Activations