© 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. 58021
    Prev
    Next
    INDEX
    Explanations

    a weekly

    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
    éªŀ
    -0.10
    æ¡¢
    -0.10
    elman
    -0.10
    åŀŃ
    -0.10
    å°Ķæĸ¯
    -0.10
    èį¤
    -0.10
    CallableWrapper
    -0.09
    åłªç§°
    -0.09
    å¼Ģåľº
    -0.09
    çĻ¾å¹´
    -0.09
    POSITIVE LOGITS
    æĹ¨åľ¨
    0.10
     initiative
    0.09
    pd
    0.09
    .tool
    0.09
     attempt
    0.08
     PD
    0.08
     cop
    0.08
    湫
    0.08
    pm
    0.08
    ãĥķãĥĪ
    0.08
    Activations Density 0.143%

    No Known Activations