© 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. 39311
    Prev
    Next
    INDEX
    Explanations

    band names

    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
    ä¸Ģå¼ł
    -0.09
    åĨķ
    -0.09
    ãĥĥãĥĪ
    -0.09
    Globals
    -0.09
     Freed
    -0.08
     Curse
    -0.08
    åĽĽåij¨
    -0.08
    ibu
    -0.08
    oyer
    -0.08
    gro
    -0.08
    POSITIVE LOGITS
    äºī缸
    0.09
    æĥħæĬ¥
    0.09
    ernels
    0.09
    éľŀ
    0.09
    ä»ħ代表
    0.09
    干线
    0.09
    hdl
    0.08
    æĥ¯
    0.08
    ishment
    0.08
    pliance
    0.08
    Activations Density 0.010%

    No Known Activations