© 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. 6014
    Prev
    Next
    INDEX
    Explanations

    objects and places

    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
    äºĨ大éĩıçļĦ
    -0.09
    Issuer
    -0.09
    å®ŀçī©
    -0.08
     rom
    -0.08
    oci
    -0.08
    èĽĻ
    -0.08
     ÑģобÑģÑĤвенно
    -0.08
     Rom
    -0.08
    çľ¼çIJĥ
    -0.08
    æ²¥
    -0.08
    POSITIVE LOGITS
    resse
    0.09
     Bundle
    0.09
     бо
    0.09
    æĪĸèĢħåħ¶ä»ĸ
    0.09
    æĪĸåħ¶ä»ĸ
    0.09
    çĥ
    0.09
    ricks
    0.08
    ä¸Ģéģĵ
    0.08
    vented
    0.08
    èµ·åĪ°
    0.08
    Activations Density 0.393%

    No Known Activations