© 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. 3000
    Prev
    Next
    INDEX
    Explanations

    wood, tape, dye, foam, lettering

    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
    SETS
    -0.10
    çIJ¥
    -0.09
    泸
    -0.08
    åĪ¶æľį
    -0.08
    fore
    -0.08
    eeee
    -0.08
    èĢģ人家
    -0.08
    ç»ıå¼Ģ
    -0.08
     whe
    -0.08
    éķĢ
    -0.08
    POSITIVE LOGITS
    çĶµå·¥
    0.09
    äºĭåħĪ
    0.09
    ãĤ¬ãĤ¤
    0.09
    æĪĸèĢħåħ¶ä»ĸ
    0.08
    Opaque
    0.08
    oggler
    0.08
    åij¨åĪĬ
    0.08
    ὶ
    0.08
    为æѤ
    0.08
    ]|[
    0.08
    Activations Density 0.185%

    No Known Activations