© 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. 20561
    Prev
    Next
    INDEX
    Explanations

    hydrogen, atoms, and matter

    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
    溢价
    -0.11
    жд
    -0.10
    追
    -0.10
    è¾Ħ
    -0.10
    liner
    -0.09
    èĦĤ
    -0.09
    追赶
    -0.09
    Beat
    -0.09
    计è¾ĥ
    -0.09
    åĬ³ç´¯
    -0.09
    POSITIVE LOGITS
    åĪĨåŃIJ
    0.10
    æıIJçĤ¼
    0.10
    åİŁåŃIJ
    0.09
    adam
    0.09
    çī©è´¨
    0.09
    æ±½
    0.09
     atoms
    0.08
    æĤĦæĤĦ
    0.08
     atom
    0.08
    çĤ¼
    0.08
    Activations Density 0.079%

    No Known Activations