© 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. 60922
    Prev
    Next
    INDEX
    Explanations

    commissioned work

    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
    ursor
    -0.09
    vez
    -0.09
    низ
    -0.09
    顺
    -0.09
    åij³
    -0.08
    ÑģилÑĮ
    -0.08
    enstein
    -0.08
     tension
    -0.08
    omp
    -0.08
    Tween
    -0.08
    POSITIVE LOGITS
    å·²ä¹ħçļĦ
    0.10
    è¼
    0.10
    缨
    0.09
    æ¤Ł
    0.09
    å·²ä¹ħ
    0.09
    ÑĮе
    0.09
    andan
    0.09
    ´
    0.09
    äºĨä¸Ģæī¹
    0.09
    erce
    0.09
    Activations Density 0.012%

    No Known Activations