© 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. 19158
    Prev
    Next
    INDEX
    Explanations

    NIH and NCBI related organizations

    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
    åħļåĴĮåĽ½å®¶
    -0.12
    è°ģçŁ¥
    -0.11
    沿éĢĶ
    -0.10
    çıħ
    -0.09
    åĪ¨
    -0.09
    åĭĭ
    -0.09
    çĶ¨æ°´
    -0.09
    ãĥ¬ãĥĵãĥ¥ãĥ¼
    -0.09
    æĸ¥
    -0.09
    æĦŁäºº
    -0.09
    POSITIVE LOGITS
    zos
    0.10
    åħ´è¶£
    0.09
     ÑħÑĢ
    0.09
    çļĦåħ´è¶£
    0.08
    èĬ¯
    0.08
    ordinate
    0.08
    æī£
    0.08
    æķ£
    0.08
    gary
    0.08
    rawn
    0.08
    Activations Density 0.005%

    No Known Activations