© 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. 21361
    Prev
    Next
    INDEX
    Explanations

    in a sense

    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¸ĭä¸Ģ代
    -0.09
    ove
    -0.09
    æīĵçĿĢ
    -0.09
    æī¾åĩĨ
    -0.09
    oren
    -0.09
    å¹ķ
    -0.08
     Cert
    -0.08
    æĪijåıijçİ°
    -0.08
    çªģçł´åı£
    -0.08
    tract
    -0.08
    POSITIVE LOGITS
    æĦıä¹īä¸Ĭ
    0.22
    æĦıä¹īä¸ĬçļĦ
    0.21
    æĦıä¹ī
    0.15
     sense
    0.14
    çļĦæĦıä¹ī
    0.12
    æĦı義
    0.12
    éĩįè¦ģæĦıä¹ī
    0.12
    çĭŃ
    0.10
    å¼ĢéŨ
    0.10
    æĦıæĢĿ
    0.10
    Activations Density 0.048%

    No Known Activations