© 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. 56634
    Prev
    Next
    INDEX
    Explanations

    treasure, valuable, gem, precious

    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
    allon
    -0.11
    olon
    -0.10
    Raised
    -0.09
    åĢĴå¡Į
    -0.09
    诸
    -0.09
    å´©
    -0.09
    ijing
    -0.09
    çļĦç¨ĭ度
    -0.08
    çĩ®
    -0.08
    اÙĥ
    -0.08
    POSITIVE LOGITS
    å®Ŀè´µçļĦ
    0.24
    å®Ŀè´µ
    0.22
    å®ĿèĹı
    0.19
    çıįè´µ
    0.18
     treasure
    0.18
    çıį
    0.17
     valuable
    0.16
    çıįæĥľ
    0.15
     treasures
    0.15
     invaluable
    0.15
    Activations Density 0.082%

    No Known Activations