© 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. 53249
    Prev
    Next
    INDEX
    Explanations

    preparing or attempting

    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
    å½ĵæĻļ
    -0.11
    å½ĵæĹ¥
    -0.10
    æŃ£åľ¨
    -0.10
    缮åīįæŃ£åľ¨
    -0.09
    åIJ¦
    -0.09
     деÑĢ
    -0.09
    ä¸ĢçĽ´åľ¨
    -0.08
    åŁºæľ¬åİŁåĪĻ
    -0.08
     intended
    -0.08
     Vanguard
    -0.08
    POSITIVE LOGITS
    ãĤ«ãĥ³
    0.10
    ä½ĵä¼ļåĪ°
    0.09
    åĬªåĬĽ
    0.09
    æķ²
    0.09
    å°Ĩåħ¶
    0.09
    æĪĸå°Ĩ
    0.09
    eled
    0.09
    asel
    0.09
    ä¿ĿæĮģ
    0.08
    æĬĬè¿Ļ个
    0.08
    Activations Density 0.218%

    No Known Activations