© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21026
    Prev
    Next
    INDEX
    Explanations

    Nazi and German relations

    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
    ми
    -0.12
    åħħåĪĨä½ĵçİ°
    -0.10
    èİĺ
    -0.09
    èĩªå¦Ĥ
    -0.09
    å¢ī
    -0.09
    åĩĽ
    -0.08
    soles
    -0.08
    ç¯Ļ
    -0.08
    åı¤ä»Ĭ
    -0.08
    umin
    -0.08
    POSITIVE LOGITS
    -era
    0.12
    Germany
    0.11
    å¾·åĽ½
    0.09
    lector
    0.09
     Germany
    0.09
     germany
    0.09
    /ne
    0.09
    ·»
    0.09
     kep
    0.08
     ÑĢаÑģ
    0.08
    Activations Density 0.017%

    No Known Activations