© 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. 52083
    Prev
    Next
    INDEX
    Explanations

    ensure your

    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
    èļ±
    -0.09
    èĦijåŃIJ
    -0.08
    пал
    -0.08
    管åĪ¶
    -0.08
     Advis
    -0.08
    çĩł
    -0.08
    æµģæ°´
    -0.08
    éĢ¾
    -0.08
     Ful
    -0.08
    èı½
    -0.07
    POSITIVE LOGITS
    趾
    0.10
    æĶ¶åĪ°
    0.10
    _colour
    0.09
    æĤ¨çļĦ
    0.09
    è£ħ
    0.09
    åħ¸
    0.09
    ä½łçļĦ
    0.09
    åĪ»çĶ»
    0.09
    çĪ¸
    0.08
    èİĺ
    0.08
    Activations Density 0.160%

    No Known Activations