© 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. 36876
    Prev
    Next
    INDEX
    Explanations

    professional licensing or credentials

    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
    ucking
    -0.09
    _party
    -0.09
    éĹªåħī
    -0.09
    çĥŁçģ«
    -0.08
    æĿ¡çº¦
    -0.08
    ij
    -0.08
    Flip
    -0.08
    çªį
    -0.08
    _flip
    -0.08
    精确
    -0.08
    POSITIVE LOGITS
    æī§
    0.10
    è¯ģåĪ¸äº¤æĺĵ
    0.10
    èµĦæł¼
    0.10
    çĶ¨èĩªå·±çļĦ
    0.09
    åĽŀå½Ĵ
    0.09
    æ¡©
    0.09
    æĺ¯ä¸Ģéĥ¨
    0.09
    âľķ
    0.09
    ç»ĺ
    0.09
    åIJĦåİ¿
    0.09
    Activations Density 0.121%

    No Known Activations