© 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. 5571
    Prev
    Next
    INDEX
    Explanations

    mail or postal delivery

    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
    æ±ģ
    -0.10
    è¾ķ
    -0.09
    åĸ·
    -0.09
    éģĵè·¯ä¸Ĭ
    -0.09
    /music
    -0.09
    æĬ¢æķij
    -0.09
     Câm
    -0.08
    quate
    -0.08
    iant
    -0.08
    .jet
    -0.08
    POSITIVE LOGITS
    -away
    0.10
    åĩºåİ»
    0.09
    .bo
    0.09
    èĥĮ
    0.08
    åħ¨æĻ¯
    0.08
     rom
    0.08
     bo
    0.08
    带走
    0.08
     Rom
    0.08
     invalidated
    0.08
    Activations Density 0.049%

    No Known Activations