© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7264
    Prev
    Next
    INDEX
    Explanations

    all / entire / total

    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
    åĸī
    -0.10
    丧
    -0.10
    aty
    -0.09
     нед
    -0.08
    osti
    -0.08
    æĬµ
    -0.08
    ghost
    -0.07
    笤
    -0.07
    BV
    -0.07
    inic
    -0.07
    POSITIVE LOGITS
    èµĦæºIJåħ±äº«
    0.11
    æķ´ä½ĵ
    0.10
     Murdoch
    0.10
    åħ¶ä»ĸ人
    0.10
    åħ¬çĶ¨
    0.10
    æ¦ľ
    0.10
    ä¸ĭè°ĥ
    0.09
     Tüm
    0.09
    课å¤ĸ
    0.09
    大家ä¸Ģèµ·
    0.09
    Activations Density 0.224%

    No Known Activations