© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8379
    Prev
    Next
    INDEX
    Explanations

    grooves and recesses

    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
    tran
    -0.09
    æļĸ
    -0.09
    æĬķåħ¥åĪ°
    -0.09
    åĻİ
    -0.09
    è´¶
    -0.09
     station
    -0.09
    ä»İæł¹æľ¬ä¸Ĭ
    -0.09
    æī¬
    -0.09
    讫
    -0.09
    andex
    -0.08
    POSITIVE LOGITS
    åĩ¹
    0.12
    èĬ±çº¹
    0.11
    槽
    0.11
    éĽķåĪ»
    0.10
    éĵŃ
    0.10
    åĪ»
    0.10
    åĿİåĿ·
    0.10
    åį°è®°
    0.10
    çijķçĸµ
    0.09
    åįī
    0.09
    Activations Density 0.273%

    No Known Activations