© 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. 62576
    Prev
    Next
    INDEX
    Explanations

    geographic locations and social groups

    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
    éĢ¢
    -0.09
    æ¯ĶåĪ©
    -0.09
    æĪijçĪ±ä½ł
    -0.09
    ardi
    -0.08
    çĶ³åįļ
    -0.08
    ature
    -0.08
    沪
    -0.08
    SO
    -0.08
    ç½ij讯
    -0.08
    asic
    -0.08
    POSITIVE LOGITS
    ä¸ĢèĪ¬äºº
    0.11
    åħ³éŨ
    0.10
    çĻ¾å§ĵ
    0.10
    æĭ©
    0.09
    å±ħå§Ķä¼ļ
    0.09
    ASE
    0.09
    è¿Ļä¸įæĺ¯
    0.09
    place
    0.09
    è½Ń
    0.08
    山谷
    0.08
    Activations Density 0.061%

    No Known Activations