© 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. 55678
    Prev
    Next
    INDEX
    Explanations

    bowl, dish, derivative, cups

    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
    elen
    -0.11
    管ç½ij
    -0.09
    ergic
    -0.09
    ynchronously
    -0.09
    ien
    -0.09
    iring
    -0.09
    IENT
    -0.08
    çĤĻ
    -0.08
    chs
    -0.08
    fone
    -0.08
    POSITIVE LOGITS
     Forgotten
    0.09
    欢è¿İæĤ¨
    0.09
    è®¤çľŁåŃ¦ä¹ł
    0.09
    æĭĬ
    0.09
    çĶ¨å·¥
    0.08
    éĶ¹
    0.08
    ä¸Ńéĵģ
    0.08
    ä¸Ńæĸ¹
    0.08
    湿润
    0.08
    çĶ¨æ°´
    0.08
    Activations Density 0.007%

    No Known Activations