© 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. 38186
    Prev
    Next
    INDEX
    Explanations

    try to verb

    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
    æķ¦
    -0.11
    éĤ£ä»½
    -0.09
    è¿ĻåĿĹ
    -0.09
    åĽºçĦ¶
    -0.09
    _utilities
    -0.09
    OTO
    -0.08
    ä¸ĢæŶ
    -0.08
    æīĢè°ĵ
    -0.08
    å½¼
    -0.08
    æīįèĥ½
    -0.08
    POSITIVE LOGITS
    å°½éĩı
    0.11
    åģļçļĦ
    0.10
    pill
    0.09
    éģ¿åħį
    0.09
    å¤ķ
    0.09
    åı¯è§Ĩ
    0.09
    æľĢå°ij
    0.09
    anya
    0.09
    look
    0.08
    çĿĢçľ¼äºİ
    0.08
    Activations Density 0.046%

    No Known Activations