© 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. 19133
    Prev
    Next
    INDEX
    Explanations

    words following "said" or "asked"

    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
    çī¹åĪ«æĺ¯åľ¨
    -0.10
    该éĻ¢
    -0.10
    åĽ½åľŁ
    -0.10
    纵横
    -0.10
    ä¼ļåıijçĶŁ
    -0.10
    éĺĩ
    -0.09
    æµ·åĨħå¤ĸ
    -0.09
    çĶ¨æĪ·æıIJä¾Ľ
    -0.09
    agher
    -0.09
    çŁŃæľŁåĨħ
    -0.09
    POSITIVE LOGITS
    æĬij
    0.08
    积æŀģæİ¨è¿Ľ
    0.08
    æīĵæĸŃ
    0.08
    å¹½
    0.08
    EventData
    0.08
    vr
    0.07
    å¾Īæľī
    0.07
    Ùģرد
    0.07
    çĽ¸ä¿¡å¤§å®¶
    0.07
    ç´§è·Ł
    0.07
    Activations Density 0.011%

    No Known Activations