© 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. 29722
    Prev
    Next
    INDEX
    Explanations

    file format support, color, flow, arel

    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
    çĪ·
    -0.10
    Balancer
    -0.09
    Addon
    -0.08
     Ñģеб
    -0.08
    æķıæĦŁ
    -0.08
    edm
    -0.08
    æĺ¾éľ²
    -0.08
     ëĦĪ
    -0.08
    ðŁİ¤
    -0.08
    ä¸įè´Ł
    -0.08
    POSITIVE LOGITS
    å¿ĥ缮ä¸Ń
    0.11
    åįģä¸ĩ
    0.10
    åĬłæ·±
    0.10
    å¼Ĥ
    0.09
    榴
    0.09
    ä¸ĢåľĪ
    0.09
    èŀº
    0.09
    æĬĺ
    0.08
    èĪ¶
    0.08
    究竣
    0.08
    Activations Density 0.002%

    No Known Activations