© 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. 18156
    Prev
    Next
    INDEX
    Explanations

    garden, plants, pots

    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
    æĿijå§Ķä¼ļ
    -0.09
    ä¸Ŀ绸ä¹ĭè·¯
    -0.08
     Rough
    -0.08
    esen
    -0.08
    ieber
    -0.08
    ç¼²
    -0.08
    çĩ§
    -0.08
    åľĪåŃIJ
    -0.08
    sen
    -0.08
    çļĦåľ°æĸ¹
    -0.08
    POSITIVE LOGITS
    ç¨Ģ
    0.13
    æł½åŁ¹
    0.12
    çĽĨ
    0.12
     pot
    0.11
    æ¤įçī©
    0.11
    æĭ¿
    0.10
    åħ»æĬ¤
    0.10
    çIJī
    0.09
     pots
    0.09
    èĭĹ
    0.09
    Activations Density 0.077%

    No Known Activations