© 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. 11239
    Prev
    Next
    INDEX
    Explanations

    resurfacing, refitting, refolding

    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
    åı¯æĢľ
    -0.11
    æľīèī²
    -0.09
    弧
    -0.09
    ä¸įæĩĤ
    -0.09
    æľµ
    -0.09
    ç½ijé¦ĸ页
    -0.09
    ç»ĵæŀĦè°ĥæķ´
    -0.09
    çīĴ
    -0.09
    çĿ¨
    -0.08
    å°º
    -0.08
    POSITIVE LOGITS
    åij¼å£°
    0.09
    ihn
    0.09
    uden
    0.09
    etr
    0.08
    ano
    0.08
    ingle
    0.08
    rate
    0.08
    æĦıæĦ¿
    0.08
    ub
    0.08
     br
    0.08
    Activations Density 0.007%

    No Known Activations