© 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. 57353
    Prev
    Next
    INDEX
    Explanations

    North Korea; Pyongyang; Red Cross

    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
    赶紧
    -0.08
    åħ¬çĽĬ
    -0.08
    åĨħå¿ĥ
    -0.08
    ç´ł
    -0.08
    æŃ£ä¹ī
    -0.07
    请åıĬæŶ
    -0.07
    宿
    -0.07
     Sans
    -0.07
    æ²Ł
    -0.07
     гÑĢн
    -0.07
    POSITIVE LOGITS
    ebin
    0.10
    åıijå±ķ空éĹ´
    0.10
    åħĪè¿Ľåįķä½į
    0.10
    çĿ¥
    0.09
     Pyongyang
    0.09
    é«ĺ度
    0.09
    å¹²éĥ¨
    0.09
    (enum
    0.09
    磮
    0.09
    人æ°ij
    0.09
    Activations Density 0.043%

    No Known Activations