© 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. 32781
    Prev
    Next
    INDEX
    Explanations

    military service history

    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
     conj
    -0.09
    çķ´
    -0.08
    ITH
    -0.08
    ä¼ļè§ģ
    -0.08
    岿
    -0.08
    缸åĬ©
    -0.08
    èķĥ
    -0.08
    оÑĢа
    -0.08
    帮æī¶
    -0.08
    åħ´å¥ĭ
    -0.07
    POSITIVE LOGITS
    çĶ¨éĢĶ
    0.14
    è¿Ļ款
    0.11
    å®ŀçĶ¨æĢ§
    0.11
     doctr
    0.11
    主è¦ģçĶ¨äºİ
    0.10
    å®ŀçĶ¨
    0.10
    æĢ§èĥ½
    0.10
    åİŁåŀĭ
    0.10
    æľįå½¹
    0.10
    æĹ©æľŁ
    0.10
    Activations Density 0.298%

    No Known Activations