© 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. 51236
    Prev
    Next
    INDEX
    Explanations

    that/who followed by a verb

    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
    ä»»ä½ķ人éĥ½
    -0.10
    atori
    -0.09
     generally
    -0.09
    รà¸Ńย
    -0.08
    INI
    -0.08
    å¦Ĥæŀľä¸įæĺ¯
    -0.08
    åĩĨ
    -0.08
    åĩłä¹İæīĢæľī
    -0.08
    鸥
    -0.08
    ä»£æĽ¿
    -0.08
    POSITIVE LOGITS
    çļĦä¸ĢåĪĩ
    0.09
    以人为
    0.09
    WER
    0.09
    å±ĤéĿ¢
    0.09
    irms
    0.08
    çĸĻ
    0.08
     readline
    0.08
    ibel
    0.08
    andest
    0.08
    红æŀ£
    0.08
    Activations Density 0.250%

    No Known Activations