© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30754
    Prev
    Next
    INDEX
    Explanations

    commitment to future expansion

    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
    æ¯ĶæĪij
    -0.10
    æĦķ
    -0.10
    AGE
    -0.09
    ÑĤеÑĢ
    -0.08
    微信群
    -0.08
    azel
    -0.08
     Bauer
    -0.08
    æ¶Ī失äºĨ
    -0.08
    éĩijéĴ±
    -0.08
    笮
    -0.07
    POSITIVE LOGITS
    èĩ´åĬĽäºİ
    0.12
    ä¸Ģè´¯
    0.12
    è·µ
    0.11
    贯彻
    0.10
    海滨
    0.10
    èĩ´åĬĽ
    0.10
    追æ±Ĥ
    0.10
    å®ĹæŨ
    0.10
    å»ī
    0.09
    æŀ¯
    0.09
    Activations Density 0.049%

    No Known Activations