© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 36677
    Prev
    Next
    INDEX
    Explanations

    changing schools, servers, houses

    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¬è¯·
    -0.09
    liner
    -0.09
    erno
    -0.09
     fe
    -0.09
    èħ°éĥ¨
    -0.08
    unan
    -0.08
    annel
    -0.08
    _middle
    -0.08
    è§Ĥæµĭ
    -0.08
    ennie
    -0.08
    POSITIVE LOGITS
    æĺ¯ä¸Ģä»¶
    0.10
    ogn
    0.09
    acl
    0.09
    è¾Ļ
    0.08
    Arena
    0.08
    累累
    0.08
    æijĦ
    0.08
    kat
    0.08
    èĪĴ
    0.08
    ë§ģ
    0.08
    Activations Density 0.063%

    No Known Activations