© 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. 51711
    Prev
    Next
    INDEX
    Explanations

    license or sale

    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
    ifik
    -0.09
     Rams
    -0.09
    æĺĨä»ij
    -0.09
    æµ·æĬ¥
    -0.09
    è·³è·ĥ
    -0.08
     ÙĪÙĩ
    -0.08
    èĽ©
    -0.08
    åıijå±ķ壮大
    -0.08
    .ascii
    -0.08
    èŃ
    -0.08
    POSITIVE LOGITS
    æłĩåĩĨåĮĸ
    0.10
    orce
    0.09
     eh
    0.09
    vo
    0.09
    管家
    0.08
    è§ĦèĮĥåĮĸ
    0.08
    ividual
    0.08
    éģĵè·¯ä¸Ĭ
    0.08
    ä¸ĩéĩĮ
    0.08
    ower
    0.08
    Activations Density 0.001%

    No Known Activations