© 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. 3851
    Prev
    Next
    INDEX
    Explanations

    legal cases and finance

    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
    è´¨éĩıéĹ®é¢ĺ
    -0.08
    丧
    -0.08
    æ²Ļæ¼ł
    -0.08
    èº²åľ¨
    -0.08
    è´¸æĺĵ
    -0.08
     protesting
    -0.08
    åĮĹæŀģ
    -0.08
    å½±
    -0.08
    urch
    -0.08
    êm
    -0.08
    POSITIVE LOGITS
     extrad
    0.11
    çĶŁäº§æĢ»åĢ¼
    0.10
    umd
    0.09
    æijĨæĶ¾
    0.09
    åħŃåIJĪ
    0.09
    Witness
    0.09
     exon
    0.09
    åħ¬è¯ī
    0.08
    æ³ķå¾ĭè§Ħå®ļ
    0.08
    æ³ķåºŃ
    0.08
    Activations Density 0.766%

    No Known Activations