© 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. 38853
    Prev
    Next
    INDEX
    Explanations

    war strategy, warlord, war supplies, war winners

    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
    -scrollbar
    -0.10
    路桥
    -0.09
    éĨ´
    -0.09
    ivity
    -0.09
    Ĩ
    -0.09
    amar
    -0.08
    æĿī
    -0.08
    urator
    -0.08
    ues
    -0.08
    -heavy
    -0.08
    POSITIVE LOGITS
    rior
    0.14
    riors
    0.13
    lords
    0.12
    fully
    0.11
    pped
    0.09
    çī¹åĪ«å£°æĺİ
    0.09
    åĶ¿
    0.09
    åĩºçīĪ社
    0.09
    andes
    0.09
    nable
    0.09
    Activations Density 0.042%

    No Known Activations