© 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. 20366
    Prev
    Next
    INDEX
    Explanations

    making it

    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
    赧
    -0.10
     поÑĢÑıд
    -0.09
    好åIJĹ
    -0.09
    lich
    -0.09
    åģļå¾Ĺ
    -0.08
    æ²Ł
    -0.08
    龸çİĭ
    -0.08
    çļĦåĪ©çĽĬ
    -0.08
    åı¥
    -0.08
    ä¸į说
    -0.08
    POSITIVE LOGITS
    ä¸į失
    0.10
    å®ĥæĺ¯
    0.09
    å®ľå±ħ
    0.09
    为主è¦ģ
    0.09
    她æĺ¯
    0.08
    usi
    0.08
    河水
    0.08
    è¿Ļä¹Łæĺ¯
    0.08
    brane
    0.08
    -corner
    0.08
    Activations Density 0.025%

    No Known Activations