© 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. 56033
    Prev
    Next
    INDEX
    Explanations

    settlements, camps, and townships

    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
    OUN
    -0.10
    åĶĽ
    -0.09
    /gpl
    -0.09
    èĮ§
    -0.09
    uhl
    -0.09
    æĻķ
    -0.09
    彧
    -0.09
    æ±Ŀ
    -0.09
    ä¸Ģ个æĺ¯
    -0.09
    åıĹåĪ°äºĨ
    -0.09
    POSITIVE LOGITS
    éĩĮçļĦ
    0.12
    裡
    0.10
    éĩĮ
    0.09
    buster
    0.09
    åĢ¾åIJij
    0.08
    ниÑĩ
    0.08
    åĪĨãģij
    0.08
    åĪĿ次
    0.08
    ish
    0.08
    ï¸
    0.08
    Activations Density 0.008%

    No Known Activations