© 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. 40116
    Prev
    Next
    INDEX
    Explanations

    cytosolic

    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
    ickle
    -0.09
    åı±
    -0.09
    æŶèĬĤ
    -0.09
    stead
    -0.09
    ä¸įå·²
    -0.09
    æĵĤ
    -0.09
    دار
    -0.09
    祢
    -0.09
    åĩºæĿ¥äºĨ
    -0.08
    çŁ¥éģĵèĩªå·±
    -0.08
    POSITIVE LOGITS
     rowspan
    0.10
    ä½
    0.09
    æĬĦ
    0.09
    gan
    0.08
     colspan
    0.08
    çĵ¶
    0.08
    _regularizer
    0.08
    _backend
    0.08
    poses
    0.08
    gm
    0.08
    Activations Density 0.133%

    No Known Activations