© 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. 50146
    Prev
    Next
    INDEX
    Explanations

    assisted, was, followed, accompanied

    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
    å®ŀæĻ¯
    -0.10
    移åĬ¨
    -0.10
    å¼Ģ设
    -0.09
    éŃij
    -0.09
    BarItem
    -0.09
    ensch
    -0.09
    ä¸į失
    -0.08
     mobile
    -0.08
    éĥģéĹ·
    -0.08
    æĺİæľĹ
    -0.08
    POSITIVE LOGITS
    ä¼´
    0.15
     followed
    0.15
     accompanied
    0.14
    åij¨åĽ´
    0.14
    ä¼´éļıçĿĢ
    0.14
    åIJİéĿ¢
    0.13
    身边çļĦ
    0.13
    ç´§æİ¥çĿĢ
    0.13
    ä¼´æľī
    0.13
    æĹģè¾¹
    0.12
    Activations Density 0.120%

    No Known Activations