© 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. 63456
    Prev
    Next
    INDEX
    Explanations

    visitor centers and shops

    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
    ocene
    -0.09
     Duis
    -0.09
    æĻ®æ³ķ
    -0.08
    ONUS
    -0.08
    ÑįÑĤ
    -0.08
    è¸ıä¸Ĭ
    -0.08
    ä¸įçĦ¶
    -0.08
    çĿ£
    -0.08
    cki
    -0.08
    çĹ´
    -0.08
    POSITIVE LOGITS
    ä¸ĢåĪĩéĥ½
    0.09
    室
    0.08
    éŁ³
    0.08
    uesta
    0.08
    .consume
    0.08
    京津
    0.08
    大楼
    0.08
    ç¨Ĺ
    0.08
    åĮĹæĸĹ
    0.08
    ä¸ĢåĪĩ
    0.08
    Activations Density 0.009%

    No Known Activations