© 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. 27459
    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
    æĺ¯ä¸Ģ
    -0.09
    交
    -0.08
    çļĦæīĢæľī
    -0.07
    æ²»çĹħ
    -0.07
     unofficial
    -0.07
     singular
    -0.07
     Sü
    -0.07
    urch
    -0.07
    -card
    -0.07
     Complexity
    -0.07
    POSITIVE LOGITS
    æıŃå¼Ģ
    0.10
    getConnection
    0.10
    _MINOR
    0.09
    igm
    0.09
     ÐĶм
    0.09
    getReference
    0.09
    å¸ĥæľĹ
    0.08
     Willis
    0.08
    ä¹Łå¥½
    0.08
     cloak
    0.08
    Activations Density 0.751%

    No Known Activations