© 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. 7492
    Prev
    Next
    INDEX
    Explanations

    asking for help

    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
     isArray
    -0.09
    av
    -0.09
    ath
    -0.08
    avr
    -0.08
    ening
    -0.08
    ãģķãģ¾
    -0.08
    pond
    -0.08
    uren
    -0.08
    avra
    -0.08
     rá»ĵi
    -0.08
    POSITIVE LOGITS
    解æĶ¾æĢĿæĥ³
    0.12
    åĽłä¸ºæĪij们
    0.11
    å¾Īå¤ļæľĭåıĭ
    0.11
    æĺ¯ä»Ģä¹Īåij¢
    0.10
    人çĶŁçļĦ
    0.10
    åĬ©éķ¿
    0.10
    æĢĿ绪
    0.10
    åĽłä¸ºåľ¨
    0.09
    éĦĻ
    0.09
    åĽłä¸ºæĪij
    0.09
    Activations Density 0.548%

    No Known Activations