© 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. 9711
    Prev
    Next
    INDEX
    Explanations

    near infrared spectroscopy

    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
    åīįä¸ī
    -0.11
    åĪį
    -0.10
    ä¸Ģåī¯
    -0.09
    Difficulty
    -0.09
    оÑĩно
    -0.09
    éĹ¨æ§Ľ
    -0.09
    满äºĨ
    -0.09
    jee
    -0.09
    urd
    -0.09
    anter
    -0.09
    POSITIVE LOGITS
    æĭĤ
    0.11
    红å¤ĸ
    0.09
    çĸĹæ³ķ
    0.09
    大家
    0.09
    éģģ
    0.09
    åĽ½éĺ²
    0.09
    7
    0.09
    姹
    0.08
    称ä¹ĭ
    0.08
    4
    0.08
    Activations Density 0.278%

    No Known Activations