© 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. 29771
    Prev
    Next
    INDEX
    Explanations

    tool or software tags

    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
    åħį
    -0.09
    ding
    -0.09
    uru
    -0.09
    dit
    -0.08
    éĶ¤
    -0.08
    GED
    -0.08
    berger
    -0.08
    èµĸ以çĶŁåŃĺ
    -0.08
    bread
    -0.08
    isodes
    -0.08
    POSITIVE LOGITS
    à¹Ħ
    0.10
    ä¸Ģåı¥
    0.09
    ä½Ļ家
    0.09
    pects
    0.09
    ä¸įåĩĨ
    0.09
    èıľ
    0.09
    Merit
    0.09
    æĸ°ä¸ī
    0.08
    endar
    0.08
    _leave
    0.08
    Activations Density 0.001%

    No Known Activations