© 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. 34609
    Prev
    Next
    INDEX
    Explanations

    implicit meaning or considerations

    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
    outer
    -0.08
    åIJĿ
    -0.08
    è´¯
    -0.08
    over
    -0.08
     Lump
    -0.08
    amu
    -0.08
    çģĮ
    -0.07
    çĶ¥
    -0.07
     outer
    -0.07
     Niet
    -0.07
    POSITIVE LOGITS
    æļĹ示
    0.17
    éļIJ
    0.14
    éļIJéļIJ
    0.12
    é»ĺ
    0.12
    éļIJå½¢
    0.12
     IMPLIED
    0.11
    æ·±å¤Ħ
    0.11
    æľŁçĽ¼
    0.11
    æĶ¶è´¹æłĩåĩĨ
    0.11
    æ½ľåľ¨
    0.10
    Activations Density 0.042%

    No Known Activations