© 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. 39900
    Prev
    Next
    INDEX
    Explanations

    instructions for use or availability

    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
    ä¸ĢåĪĩéĥ½
    -0.10
    模èĮĥ
    -0.09
    没éĶĻ
    -0.09
    å¼ĢåѦ
    -0.09
    .Annotations
    -0.09
    èıĸ
    -0.09
    æ¡ĪåŃIJ
    -0.08
    ä¿ĿæĮģçĿĢ
    -0.08
    بط
    -0.08
    ÑĩÑĥ
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.11
    çĽ²çĽ®
    0.10
    åľ¨åIJĮä¸Ģ
    0.09
    æ´¾
    0.09
    éĶĪ
    0.09
    èĤĵ
    0.08
    ä½İäºİ
    0.08
    è¶ħè¿ĩ
    0.08
    éĵ®
    0.08
    åĩij
    0.08
    Activations Density 0.064%

    No Known Activations