© 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. 23036
    Prev
    Next
    INDEX
    Explanations

    religious organizations and institutions

    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
    èij³
    -0.09
    为导åIJij
    -0.09
    ervo
    -0.09
    éļĻ
    -0.09
    ateway
    -0.08
    ä¿Ŀåģ¥åĵģ
    -0.08
    éļį
    -0.08
    éĴ¥
    -0.08
    æĢ»çĽij
    -0.08
    æĻ´
    -0.08
    POSITIVE LOGITS
    dam
    0.10
    alia
    0.09
     scor
    0.09
    ammen
    0.09
    rew
    0.09
    æľĪä¸ĭ
    0.08
    adel
    0.08
    ington
    0.08
    amm
    0.08
     Possibly
    0.08
    Activations Density 0.004%

    No Known Activations