© 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. 36773
    Prev
    Next
    INDEX
    Explanations

    permission, consent, property, agreement, granted, prohibited

    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
    æķ¢
    -0.10
    横
    -0.09
    çİ°å®ŀçĶŁæ´»
    -0.09
    æĹģ
    -0.09
    è´¶
    -0.09
    ç¾İèģĶ
    -0.09
    uges
    -0.08
    çŀ»
    -0.08
    æľŃ
    -0.08
     pir
    -0.08
    POSITIVE LOGITS
    isi
    0.09
    æ¼±
    0.09
    缩çŁŃ
    0.09
    æµĭ
    0.09
    imo
    0.09
    KK
    0.09
    æīª
    0.08
     Jeh
    0.08
    notated
    0.08
    ""↵
    0.08
    Activations Density 0.005%

    No Known Activations