© 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. 38068
    Prev
    Next
    INDEX
    Explanations

    sea stars

    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
    éļĶ
    -0.10
    rig
    -0.10
    æ»ŀ
    -0.09
    rust
    -0.08
    为æŃ¢
    -0.08
    ÙħاÙħ
    -0.08
     Pyramid
    -0.08
    rid
    -0.08
    èݺ
    -0.08
     Bang
    -0.08
    POSITIVE LOGITS
    åħ¨æĹ¥
    0.10
    é»Ħçĵľ
    0.10
    ÅĤó
    0.10
    渤海
    0.09
    èħĶ
    0.09
    çIJ¢
    0.09
    æĪ¿ä¸ľ
    0.09
    thane
    0.09
    æĶ¾æĿ¾
    0.09
     amat
    0.09
    Activations Density 0.089%

    No Known Activations