© 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. 32782
    Prev
    Next
    INDEX
    Explanations

    damage of terminal

    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
    çĵ¶
    -0.10
    èĿ®
    -0.09
    лик
    -0.09
    çݰ身
    -0.09
    æŃ»
    -0.09
    ä¸ĢåĽ¢
    -0.09
    åĬŁèĥ½æĢ§
    -0.09
     bottle
    -0.09
    éļ½
    -0.09
    æĹ¥è®¯
    -0.08
    POSITIVE LOGITS
    é¢ijç¹ģ
    0.12
    åĨ²åĩ»
    0.11
    çĶ¨åĬĽ
    0.11
    é«ĺé¢ij
    0.10
    åºĶåĬĽ
    0.10
    ä¸įåı¯éģ¿åħį
    0.09
    éł»
    0.09
    èĭĽ
    0.09
    é«ĺ温
    0.09
    åī§çĥĪ
    0.09
    Activations Density 0.260%

    No Known Activations