© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9320
    Prev
    Next
    INDEX
    Explanations

    Weiss names or words containing Weiss

    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
    essler
    -0.10
     Andres
    -0.10
    Marshal
    -0.10
    urette
    -0.09
    ugin
    -0.09
    ëį©
    -0.09
    SPATH
    -0.09
    å¹³éĿĻ
    -0.09
    SHOT
    -0.09
    è£Ĩ
    -0.09
    POSITIVE LOGITS
    TODO
    0.09
    erta
    0.08
    l
    0.08
    è°¤
    0.08
    imate
    0.08
    ally
    0.08
    ä¸ĬçļĦ
    0.08
    家ä½ı
    0.08
    FIXME
    0.08
    äºĨä¸Ģä¸ĭ
    0.08
    Activations Density 0.007%

    No Known Activations