© 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. 58885
    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
    éĩijåŃĹå¡Ķ
    -0.10
    elia
    -0.10
    åħ³æ³¨åº¦
    -0.09
    ened
    -0.09
    éľ¹
    -0.09
    æ¸ħæī«
    -0.09
    éªģ
    -0.08
    å·½
    -0.08
    æĤ¬æĮĤ
    -0.08
    most
    -0.08
    POSITIVE LOGITS
    æѤäºĭ
    0.13
    å¾Ģäºĭ
    0.12
    ä¸Ģä¸ĭ
    0.12
    æ¦Ķ
    0.10
    äºĨä¸Ģä¼ļ
    0.10
    acles
    0.09
     whether
    0.09
    ä¸Ģ个éĹ®é¢ĺ
    0.09
    èĥ½åIJ¦
    0.09
    è¿Ļ个éĹ®é¢ĺ
    0.09
    Activations Density 0.019%

    No Known Activations