© 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. 1543
    Prev
    Next
    INDEX
    Explanations

    lists of items

    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
    æľī两个
    -0.10
    lements
    -0.09
    ä¾ĽçĶµåħ¬åı¸
    -0.09
    æľī两ç§į
    -0.09
    EventArgs
    -0.09
    isme
    -0.08
    çĤ«
    -0.08
    NEY
    -0.08
    ĶåĽŀ
    -0.08
    缸åħ³éĥ¨éŨ
    -0.08
    POSITIVE LOGITS
    çĶļèĩ³è¿ŀ
    0.10
     etc
    0.10
    çĶļèĩ³
    0.10
    åĪ«çļĦ
    0.09
    ä¸Ģæł·
    0.09
     tháºŃm
    0.09
    以åıĬåħ¶ä»ĸ
    0.09
    çĶļèĩ³æĺ¯
    0.09
    ä¹ĥèĩ³
    0.08
    Invariant
    0.08
    Activations Density 0.206%

    No Known Activations