© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12414
    Prev
    Next
    INDEX
    Explanations

    anarchist, libertarian, decentralized

    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
    Negative Logits
    rong
    -0.09
     Eld
    -0.09
    ressed
    -0.09
    rary
    -0.09
    abetes
    -0.08
    phony
    -0.08
    æīįåıijçİ°
    -0.08
    _mgmt
    -0.08
    ä¸įåħ·å¤ĩ
    -0.08
    оÑĩной
    -0.08
    POSITIVE LOGITS
    -leaning
    0.10
     ENT
    0.10
    çĬ¶æĢģä¸ĭ
    0.09
    uder
    0.09
    笥
    0.09
    ë¡Ń
    0.09
    terra
    0.09
    åĮħ容
    0.09
    åħ®
    0.09
    åIJĦè¡Į
    0.08
    Activations Density 0.013%

    No Known Activations