© 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. 4613
    Prev
    Next
    INDEX
    Explanations

    hot beverages and food

    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
    浪
    -0.10
    å¿ĥæĢĿ
    -0.09
    åij¨è½¬
    -0.08
    inine
    -0.08
     hardened
    -0.08
    anal
    -0.08
    ÑĢоÑģÑĤ
    -0.08
    ptic
    -0.08
    cular
    -0.08
    راء
    -0.08
    POSITIVE LOGITS
    æŶæĬ¥
    0.11
    æĬķèµĦé¡¹çĽ®
    0.11
    æľīä¸ĢçĤ¹
    0.10
    ä¸ĢåĿĹ
    0.10
    ä¸ĢçĤ¹
    0.09
    LOCKS
    0.09
    itti
    0.09
    çķ¥æľī
    0.09
    ifier
    0.09
    æµģè¡ĮçļĦ
    0.09
    Activations Density 0.008%

    No Known Activations