© 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. 37096
    Prev
    Next
    INDEX
    Explanations

    bad english, bad source, bad boy

    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
    Americ
    -0.09
    å¹»
    -0.09
    auc
    -0.08
    allis
    -0.08
    s
    -0.08
    cores
    -0.08
    è¹Ĭ
    -0.08
    çªħ
    -0.08
    èĻļ
    -0.08
    ãģ¹ãģį
    -0.08
    POSITIVE LOGITS
    OMBRE
    0.10
    ctors
    0.10
    ä¸ļä½Ļ
    0.09
    çĸıéĢļ
    0.09
    há»ķ
    0.09
    ä¸ŃåĽ½åĪ¶éĢł
    0.09
     nghè
    0.09
     giú
    0.09
    ÙĪÙī
    0.09
     Crossing
    0.09
    Activations Density 0.019%

    No Known Activations