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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52233
    Prev
    Next
    INDEX
    Explanations

    building and construction

    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
    SOLE
    -0.12
    ivist
    -0.11
    åŃ°
    -0.10
    ìĨĶ
    -0.10
    å¡Ĭ
    -0.10
     Hundred
    -0.10
    çªŁ
    -0.10
    æĬ¢æķij
    -0.09
    ombo
    -0.09
    åħ¨å¤©
    -0.09
    POSITIVE LOGITS
    0
    0.09
    è¯ij
    0.08
    (es
    0.08
     chap
    0.08
    é«ĺæĸ°åĮº
    0.08
    5
    0.08
     Kah
    0.07
    æµģè¡ĮçļĦ
    0.07
    2
    0.07
    1
    0.07
    Activations Density 0.031%

    No Known Activations