© 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. 57948
    Prev
    Next
    INDEX
    Explanations

    benefits and consequences

    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
    yna
    -0.09
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.09
    ä½łçŁ¥éģĵ
    -0.09
    agraph
    -0.09
    åľ¨äºİ
    -0.09
    AtIndex
    -0.08
    å¸ľ
    -0.08
    æľ¬èº«
    -0.08
    大çĽĺ
    -0.08
    为é¦ĸ
    -0.08
    POSITIVE LOGITS
    å®ģ
    0.11
    åIJİæŀľ
    0.11
     consequences
    0.10
    å®ģæĦ¿
    0.10
    çłĶ究æĪIJæŀľ
    0.10
    åĩ«
    0.10
    æĪIJæŀľ
    0.10
    ç»ĪçĶŁ
    0.09
    寧
    0.09
    ç»Ī身
    0.09
    Activations Density 0.031%

    No Known Activations