© 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. 20223
    Prev
    Next
    INDEX
    Explanations

    Holy Spirit, Ghost, demon, Witch

    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
    æģį
    -0.10
    综åIJĪæĢ§
    -0.10
    ROY
    -0.09
    ãĤīãģĦ
    -0.09
    屿
    -0.09
    ias
    -0.09
    éķª
    -0.09
     Sink
    -0.09
    aroo
    -0.08
    sst
    -0.08
    POSITIVE LOGITS
    éĻį临
    0.09
    tics
    0.09
    è±ļ
    0.09
     QObject
    0.09
    izar
    0.08
    asar
    0.08
    èĵĸ
    0.08
     Santo
    0.08
     hose
    0.08
    imas
    0.08
    Activations Density 0.006%

    No Known Activations