© 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. 38518
    Prev
    Next
    INDEX
    Explanations

    come on

    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
    èĸı
    -0.09
    éĤ¦
    -0.09
    åĬłä»¥
    -0.09
    åºĵéĩĮ
    -0.09
    æ¯ĵ
    -0.09
    ITS
    -0.09
    èĢģçĪ·
    -0.08
    å·į
    -0.08
    assy
    -0.08
    wal
    -0.08
    POSITIVE LOGITS
    RING
    0.10
    çļĩåŃIJ
    0.09
    ogo
    0.09
    elig
    0.09
    å¼ĵ
    0.08
    ãģ»ãģ¨
    0.08
    зав
    0.08
    iVar
    0.08
    åıµ
    0.08
    ynom
    0.08
    Activations Density 0.022%

    No Known Activations