© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51046
    Prev
    Next
    INDEX
    Explanations

    generating or creating

    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
    æ¸ĹéĢı
    -0.10
    è®®
    -0.09
    èĥ¨
    -0.09
    å·²ä¹ħ
    -0.09
     penet
    -0.09
    artisan
    -0.09
    èijŃ
    -0.08
    åģļä¸ĢäºĽ
    -0.08
    å¾Īä¹ħ
    -0.08
    ä¸ĥæĺŁ
    -0.08
    POSITIVE LOGITS
    æĿ¥èĩª
    0.10
     passing
    0.09
    ACP
    0.09
    çĭ¡
    0.09
    çĥŃéĩı
    0.08
     output
    0.08
    Ñįм
    0.08
    å¤ļä½Ļ
    0.08
    ç»°
    0.08
     Plex
    0.08
    Activations Density 0.535%

    No Known Activations