© 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. 1711
    Prev
    Next
    INDEX
    Explanations

    owners and related roles

    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
    åħ¨æĹ¥
    -0.10
    ä¸ĵ家ç»Ħ
    -0.09
    æ·Ļ
    -0.09
    带走
    -0.09
    ãģĭãĤĭ
    -0.09
    åĩĨåħ¥
    -0.09
    iked
    -0.08
    涵çĽĸ
    -0.08
    ãģıãĤĭ
    -0.08
     dise
    -0.08
    POSITIVE LOGITS
    å°¤åħ¶æĺ¯
    0.12
    å°Ĩèĩªå·±çļĦ
    0.11
    åıijçİ°èĩªå·±
    0.10
    æĥ³
    0.10
    æĥ³è¦ģ
    0.10
    è§īå¾Ĺèĩªå·±
    0.10
    ntl
    0.09
    çī¹åĪ«æĺ¯
    0.09
    对èĩªå·±çļĦ
    0.09
    .boot
    0.09
    Activations Density 0.144%

    No Known Activations