© 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. 8348
    Prev
    Next
    INDEX
    Explanations

    musical artists' names

    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
    äºĨ个
    -0.11
    ifen
    -0.10
    ÙĨج
    -0.09
    çĩ®
    -0.09
    ikh
    -0.09
    ä¿Ł
    -0.08
    ör
    -0.08
    URAL
    -0.08
    æ¶īåıĬåĪ°
    -0.08
    æŨ
    -0.08
    POSITIVE LOGITS
    éĽģ
    0.09
     Copp
    0.09
    çī¢
    0.09
    侥幸
    0.09
    åı©
    0.08
     Dai
    0.08
    éĢ®
    0.08
    TEM
    0.08
    otas
    0.08
    ãģıãĤĮ
    0.08
    Activations Density 0.238%

    No Known Activations