© 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. 58692
    Prev
    Next
    INDEX
    Explanations

    titles

    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
    åĪĿæģĭ
    -0.11
    ä¸ĢåĢĭ人
    -0.09
    稿件
    -0.09
    ãģıãĤĭ
    -0.08
    åįģ足
    -0.08
    ounds
    -0.08
    ductory
    -0.08
    çīº
    -0.08
    fully
    -0.08
    ession
    -0.08
    POSITIVE LOGITS
    èĩ
    0.09
    itti
    0.09
    ç®ĵ
    0.09
    -kit
    0.09
    ised
    0.08
    æݨä»ĭ
    0.08
    社ä¼ļç»Ħç»ĩ
    0.08
    æ¶ī
    0.08
    ейÑģÑĤв
    0.08
    _rw
    0.08
    Activations Density 0.014%

    No Known Activations