© 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. 32344
    Prev
    Next
    INDEX
    Explanations

    reasoning

    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
    åıªéľĢ
    -0.09
    çѱ
    -0.09
    æ³°
    -0.08
    éĩįå¿ĥ
    -0.08
     bor
    -0.08
     Bek
    -0.08
    stadt
    -0.08
    æĹ¢æĺ¯
    -0.08
    çŃĶåį·
    -0.08
    ãģĻãģİ
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.13
    åĪ«çļĦ
    0.10
    æľīå¤ļä¹Ī
    0.10
     WHETHER
    0.09
    计è¾ĥ
    0.09
    æĢ»çIJĨ
    0.09
    à¸Ľà¸ģ
    0.09
    ä½łæĥ³
    0.09
    IFO
    0.08
    esser
    0.08
    Activations Density 0.038%

    No Known Activations