© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47674
    Prev
    Next
    INDEX
    Explanations

    identifying factors, philosophy, information

    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
    antine
    -0.10
    arium
    -0.10
    ç¾ļ
    -0.09
    çħľ
    -0.09
    gMaps
    -0.09
    æĪijçļĦå¿ĥ
    -0.09
    ä¸Ĭåİ»
    -0.09
    ç¬ı
    -0.09
    sse
    -0.09
    æĸ°èĤ¡
    -0.09
    POSITIVE LOGITS
     factor
    0.10
    åĽłç´ł
    0.09
    ingly
    0.09
    伺
    0.08
     factors
    0.08
    ers
    0.08
    vol
    0.08
     agent
    0.08
    /root
    0.08
    ILING
    0.08
    Activations Density 0.123%

    No Known Activations