© 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. 52089
    Prev
    Next
    INDEX
    Explanations

    author's transl

    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
    Pod
    -0.09
    åİī
    -0.09
    омеÑĢ
    -0.09
     thôi
    -0.08
    èĭ¦éļ¾
    -0.08
     vết
    -0.08
    å¹³åİŁ
    -0.08
    à¦Ļ
    -0.08
    è²Įä¼¼
    -0.08
    çĴľ
    -0.08
    POSITIVE LOGITS
    WAYS
    0.09
    稿
    0.09
    åĮ®
    0.08
    ymes
    0.08
    lector
    0.08
     ris
    0.08
    inis
    0.08
    çĻ¾ç§ij
    0.08
    akt
    0.08
    LAT
    0.08
    Activations Density 0.069%

    No Known Activations