© 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. 22094
    Prev
    Next
    INDEX
    Explanations

    African resource development and management

    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
    alf
    -0.10
    _NB
    -0.10
    éĵ¶å·Ŀ
    -0.09
     ETA
    -0.09
    åĭ¤
    -0.08
     кваÑĢ
    -0.08
    éĥĬåĮº
    -0.08
    åĽ½éĺ²éĥ¨
    -0.08
    å¸ĥç½®
    -0.08
    ä¸ķ
    -0.08
    POSITIVE LOGITS
    èĩªçĦ¶ä¿ĿæĬ¤
    0.10
    çıį
    0.10
    çĶŁçī©
    0.10
    æĬ¢æķij
    0.09
    .bottom
    0.09
    ä¾Ŀæ³ķ
    0.09
    éĩİçĶŁåĬ¨çī©
    0.09
    æłĸ
    0.09
     protected
    0.09
     charismatic
    0.09
    Activations Density 0.118%

    No Known Activations