© 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. 6867
    Prev
    Next
    INDEX
    Explanations

    country names and locations

    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
    åıĮèħ¿
    -0.10
    楣
    -0.09
    çĿģå¼Ģ
    -0.09
    пп
    -0.09
    éĢį
    -0.09
    æ¨Ĺ
    -0.09
    å½ĵåľ°äºº
    -0.09
    éģ®
    -0.09
    好äºĭ
    -0.09
    าà¸ĩ
    -0.09
    POSITIVE LOGITS
     regions
    0.13
    é¢ĨåľŁ
    0.12
    åľ°çIJĨ
    0.11
    åľ°åĽ¾
    0.11
     ÑģÑĤÑĢанÑĭ
    0.11
    çľģ份
    0.11
    é¦ĸéĥ½
    0.11
    åĽ½åľŁ
    0.11
    å¹ħ
    0.10
    çĸĨ
    0.10
    Activations Density 0.194%

    No Known Activations