© 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. 33611
    Prev
    Next
    INDEX
    Explanations

    curcumin and related compounds

    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
    Ñĩа
    -0.09
    мел
    -0.08
    è½®å»ĵ
    -0.08
    _STS
    -0.08
    zzle
    -0.08
    overs
    -0.08
    竦
    -0.08
    å·§
    -0.08
    assa
    -0.08
    parts
    -0.08
    POSITIVE LOGITS
    izer
    0.09
    åįİ侨
    0.09
    athi
    0.09
    åIJĪåĩ»
    0.09
    èĮŃ
    0.09
    çºłçº·
    0.08
    çĨĻ
    0.08
    骧
    0.08
    èŀ³
    0.08
    累累
    0.08
    Activations Density 0.128%

    No Known Activations