© 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. 3412
    Prev
    Next
    INDEX
    Explanations

    chemistry elements and compounds

    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
     Demp
    -0.10
    oya
    -0.10
    alent
    -0.09
    éªģ
    -0.09
    éĢł
    -0.09
    åIJĪåĩ»
    -0.08
    çªĦ
    -0.08
    ино
    -0.08
    esting
    -0.08
     Helsinki
    -0.08
    POSITIVE LOGITS
     Fol
    0.10
    aten
    0.09
    åįĥéĩĮ
    0.09
    缸åħ³æĶ¿çŃĸ
    0.09
    佬
    0.08
    osit
    0.08
    诸
    0.08
    æĭ¾
    0.08
    orr
    0.08
    ovsky
    0.08
    Activations Density 0.293%

    No Known Activations