© 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. 33647
    Prev
    Next
    INDEX
    Explanations

    guar seeds or gum

    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
    aton
    -0.10
    orum
    -0.10
     gol
    -0.09
    ney
    -0.08
    (coll
    -0.08
    æijĺè¦ģ
    -0.08
     Portable
    -0.08
    BOR
    -0.08
    éªĮ
    -0.08
    shal
    -0.08
    POSITIVE LOGITS
    个人è§ĤçĤ¹
    0.10
    å·¥ä½ľç»Ħ
    0.09
    åģļåĪ°äºĨ
    0.09
    åºļ
    0.09
    æ¼ĵ
    0.08
    çļĸ
    0.08
    çŀij
    0.08
    åħ¶éĹ´
    0.08
    羨
    0.08
    åĩºåĬ¨
    0.08
    Activations Density 0.011%

    No Known Activations