© 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. 23790
    Prev
    Next
    INDEX
    Explanations

    colonel or general titles and 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
     sk
    -0.09
    çĶ·åŃ©
    -0.08
    itti
    -0.08
    主åħ¬
    -0.08
    èĬ±äºĨ
    -0.08
     blunt
    -0.08
     Cinder
    -0.08
    è´¤
    -0.08
    åIJĽ
    -0.07
    çĽı
    -0.07
    POSITIVE LOGITS
    级åĪ«çļĦ
    0.12
    ëĭĺ
    0.11
    èĢ½
    0.10
    æĮĩæĮ¥
    0.10
    级åĪ«
    0.09
    æĬ½åĩº
    0.09
    åıĬ以ä¸Ĭ
    0.09
     Proud
    0.09
    æĺ¯éĿŀ
    0.09
    antan
    0.09
    Activations Density 0.034%

    No Known Activations