© 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. 36874
    Prev
    Next
    INDEX
    Explanations

    words starting with 'fid' or 'id'

    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
    eko
    -0.09
    é¡¿
    -0.09
    ses
    -0.09
    å¿ĥ头
    -0.09
    pek
    -0.08
    è´£
    -0.08
    æĪĸå°Ĩ
    -0.08
    hton
    -0.08
    æĮ¯åħ´
    -0.08
    æ³ģ
    -0.08
    POSITIVE LOGITS
    æĢ§å¼º
    0.11
    itas
    0.10
     Cary
    0.09
     Äijáo
    0.09
    ities
    0.09
    åĪĬçī©
    0.09
    istic
    0.09
    åıµ
    0.09
     ÑįÑĤомÑĥ
    0.09
    iy
    0.09
    Activations Density 0.005%

    No Known Activations