© 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. 50654
    Prev
    Next
    INDEX
    Explanations

    cell carcinoid

    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
    éĵ¾
    -0.10
    æľīæĦıä¹ī
    -0.10
    -chain
    -0.09
    被æīĵ
    -0.09
    åĪĽæĸ°åŀĭ
    -0.09
    chain
    -0.09
    æ´Ĺ
    -0.09
     unsub
    -0.09
    æ²¾
    -0.09
     chain
    -0.09
    POSITIVE LOGITS
    çĤī
    0.09
     MEP
    0.08
    çĻ¾å®¶
    0.08
    ä¿İ
    0.08
    ÑĤÑĢÑĥд
    0.08
    division
    0.08
    chl
    0.08
    hunt
    0.08
    å°ıåĦ¿
    0.08
    çĵ¦
    0.08
    Activations Density 0.108%

    No Known Activations