© 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. 54466
    Prev
    Next
    INDEX
    Explanations

    paranormal, supernatural, parapsychology

    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
    ough
    -0.10
    ä¸į论æĺ¯
    -0.10
    ral
    -0.08
     dÃłng
    -0.08
    æģº
    -0.08
    icers
    -0.08
    agh
    -0.08
    éķ¿è¿ľ
    -0.08
     parach
    -0.08
    .Lang
    -0.08
    POSITIVE LOGITS
    horn
    0.12
    -minded
    0.10
    idade
    0.10
    ä¸Ŀä¸Ŀ
    0.10
    çݰ象
    0.09
    ity
    0.09
    åĬĽéĩı
    0.09
    çĶ¨åĵģ
    0.09
    éļĻ
    0.09
    ists
    0.08
    Activations Density 0.007%

    No Known Activations