© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54561
    Prev
    Next
    INDEX
    Explanations

    interpretation of biblical texts

    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
    寡
    -0.10
    å½ķ
    -0.10
    æĶĺ
    -0.10
    æĶĢ
    -0.09
    ä¸ĭä¸Ģ
    -0.09
    å¨ģ
    -0.09
    çī¹æĸ¯
    -0.09
    ç¾½
    -0.09
    meld
    -0.08
    æĥ³æĥ³
    -0.08
    POSITIVE LOGITS
    .parse
    0.10
    解读
    0.10
     Interpret
    0.10
     interpretation
    0.10
    interpret
    0.10
    .Parse
    0.10
     parse
    0.10
     interpret
    0.09
    base
    0.09
    çŃł
    0.09
    Activations Density 0.046%

    No Known Activations