© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21866
    Prev
    Next
    INDEX
    Explanations

    Christ's church leaders holidays

    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
    èĬ«
    -0.09
    溷
    -0.09
    åŀ«
    -0.09
    éĩįéĩijå±ŀ
    -0.09
    稳
    -0.08
    éĺ¶æ¢¯
    -0.08
     Mixing
    -0.08
    å¤ĸæı´
    -0.08
    èĩªåĪ¶
    -0.08
    è¾±
    -0.08
    POSITIVE LOGITS
    éĹ®åĢĻ
    0.09
    è´Łè´£ä»»
    0.09
    .CreateInstance
    0.09
     Ske
    0.09
    éĥijéĩį
    0.08
    å¾ĺå¾Ĭ
    0.08
    .Branch
    0.08
    ä¿İ
    0.08
    .ops
    0.08
     éĶ
    0.08
    Activations Density 0.017%

    No Known Activations