© 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. 53368
    Prev
    Next
    INDEX
    Explanations

    units of text or data

    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
    èĢĥéªĮ
    -0.10
    ooks
    -0.10
    çĶµéĩı
    -0.09
    éļıæŶéļıåľ°
    -0.09
    å¿ĥçĸ¼
    -0.09
    娣
    -0.09
    æĪIJ绩åįķ
    -0.09
    åĽ½å®¶å®īåħ¨
    -0.09
    ook
    -0.09
    .Skip
    -0.09
    POSITIVE LOGITS
    èĥ¸
    0.10
    ä¸Ńæľī
    0.10
    Ars
    0.09
    å¤ļä½ĻçļĦ
    0.08
    计éĩı
    0.08
    æĹ©æĻ¨
    0.08
    âĹĪ
    0.08
    以èī²
    0.08
    .Throw
    0.08
    alth
    0.08
    Activations Density 0.003%

    No Known Activations