© 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. 10771
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    lage
    -0.09
    è°¯
    -0.09
    裤
    -0.09
    èĪ¶
    -0.09
    æīģ
    -0.09
     bar
    -0.08
     пÑĢедлаг
    -0.08
    æµ´
    -0.08
    ç§ijæĬĢè¿ĽæŃ¥
    -0.08
    ears
    -0.08
    POSITIVE LOGITS
    åĪ°æľĢåIJİ
    0.10
    AndView
    0.10
    LOCKS
    0.09
    次è¦ģ
    0.09
    achen
    0.09
     BBC
    0.09
    åı¯æĥ³
    0.09
    imate
    0.08
    èĩ³ä¸Ĭ
    0.08
    ãĢĤï¼Į
    0.08
    Activations Density 0.008%

    No Known Activations