© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9388
    Prev
    Next
    INDEX
    Explanations

    giving up

    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
    lesh
    -0.12
    空
    -0.10
    æī£
    -0.09
    mvc
    -0.08
    .vstack
    -0.08
    пÑĥÑĤ
    -0.08
    bst
    -0.08
    BST
    -0.08
    ç¥ŀç§ĺ
    -0.08
    çĿĢ
    -0.08
    POSITIVE LOGITS
    æĶ¾å¼ĥäºĨ
    0.16
    æĶ¾å¼ĥ
    0.15
    ç»ĿæľĽ
    0.12
    è¾ĩ
    0.12
     despair
    0.12
    éªIJ
    0.11
    æ®Ĩ
    0.11
     abandon
    0.10
     abandoned
    0.10
    çĤ
    0.10
    Activations Density 0.033%

    No Known Activations