© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60853
    Prev
    Next
    INDEX
    Explanations

    affinity chromatography

    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
    é«¡
    -0.11
    建æĿIJ
    -0.10
    ä¸Ģéģĵ
    -0.10
    ä¾ł
    -0.08
    ä¸Ģ身
    -0.08
    é»Ħéĩij
    -0.08
     Cove
    -0.08
    æł¹æľ¬
    -0.08
    è¶ħ级
    -0.08
    åĬ²
    -0.08
    POSITIVE LOGITS
    åѤ
    0.11
    æĭĪ
    0.09
    iesel
    0.09
    RITE
    0.09
    轺
    0.09
     prov
    0.08
    åĵ®åĸĺ
    0.08
    éĤ£ä¹Ī容æĺĵ
    0.08
    ampo
    0.08
    æĮĤéĴ©
    0.08
    Activations Density 0.320%

    No Known Activations