© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38484
    Prev
    Next
    INDEX
    Explanations

    next day

    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
    æĹłå¥Ī
    -0.11
    éļ¾åħį
    -0.10
    ä»İåݻ年
    -0.10
    éĥģéĹ·
    -0.10
    为éĩįçĤ¹
    -0.10
    æIJĶ
    -0.09
    ourage
    -0.09
    头çĸ¼
    -0.09
    åł¡
    -0.09
    æĶ¾çľ¼
    -0.09
    POSITIVE LOGITS
    æŶ任
    0.13
    å½ĵæŶ
    0.13
    ä»İæѤ
    0.12
    å½ĵæŶçļĦ
    0.12
    çķ¶æĻĤ
    0.11
    éĤ£æŶ
    0.10
    å½ĵåľº
    0.10
    æĪijå½ĵæŶ
    0.10
    å½ĵåį³
    0.10
    èĩªæѤ
    0.10
    Activations Density 0.087%

    No Known Activations