© 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. 51567
    Prev
    Next
    INDEX
    Explanations

    success or failure

    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
    åıijçĹħçİĩ
    -0.09
    ç»Ļä»ĸ们
    -0.08
    emma
    -0.08
    rib
    -0.08
    ç»ĻäºĨ
    -0.08
    åıªè§ģ
    -0.08
    çŃĶ
    -0.08
    åħħ
    -0.08
    ä¸į该
    -0.08
    çĶĺ
    -0.08
    POSITIVE LOGITS
     attempts
    0.10
    çļĦåĬªåĬĽ
    0.10
    _attempts
    0.10
    çķĻä½ı
    0.10
    å¤ĸåĽ´
    0.09
    éĿŀè¦ģ
    0.09
    ä¼ļå¼ķèµ·
    0.09
    å°Ŀè¯ķ
    0.09
     Attempts
    0.09
    æħ®
    0.09
    Activations Density 0.044%

    No Known Activations