© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4064
    Prev
    Next
    INDEX
    Explanations

    met people

    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
    è¯įæĿ¡
    -0.11
    éķ¿è¾¾
    -0.10
    maf
    -0.08
    èļĵ
    -0.08
    è¾¾æłĩ
    -0.08
    è¾ĥéķ¿
    -0.08
    æģĭæĥħ
    -0.08
    ĥģ
    -0.08
    care
    -0.08
    çĶ©
    -0.08
    POSITIVE LOGITS
     Meet
    0.11
    缸è¯Ĩ
    0.11
     meet
    0.11
    客æĪ·éľĢæ±Ĥ
    0.10
    Meet
    0.10
    çİ®
    0.10
    ieu
    0.10
    åķĨçĶ¨
    0.10
    åĨ·éĿĻ
    0.10
    iew
    0.09
    Activations Density 0.058%

    No Known Activations