© 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. 50618
    Prev
    Next
    INDEX
    Explanations

    European countries or organizations

    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
    поÑĤ
    -0.11
    ÙŃ
    -0.10
    éĶĪ
    -0.09
    RAFT
    -0.09
    inters
    -0.09
    оп
    -0.09
    Craft
    -0.09
     Commons
    -0.08
    تÙģس
    -0.08
    reno
    -0.08
    POSITIVE LOGITS
    欧洲
    0.13
    æĪIJåijĺåĽ½
    0.11
    æ¬§çĽŁ
    0.11
    åĽŀåĽ½
    0.11
    translated
    0.10
    è·¨åĽ½
    0.10
    æľ¬åĽ½
    0.10
    åĽ½éĻħåIJĪä½ľ
    0.10
     European
    0.10
    è£Ķ
    0.10
    Activations Density 0.265%

    No Known Activations