© 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. 9685
    Prev
    Next
    INDEX
    Explanations

    on records

    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
    以åīį
    -0.10
    çĸ£
    -0.09
    ãģĦãģĭ
    -0.09
    次ä¼ļè®®
    -0.08
    chef
    -0.08
     пÑĢинÑıл
    -0.08
    شع
    -0.08
    åİŁæľ¬
    -0.08
    ottom
    -0.08
    .getBody
    -0.08
    POSITIVE LOGITS
    å¤ĸçķĮ
    0.10
    大è¡Ĺ
    0.10
    人们对
    0.09
    太å°ij
    0.09
    apollo
    0.09
    è¾ĥ强çļĦ
    0.09
    ç»Į
    0.09
     trÃŃ
    0.09
    _frames
    0.08
    Staff
    0.08
    Activations Density 0.041%

    No Known Activations