© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51629
    Prev
    Next
    INDEX
    Explanations

    synthetic and chemical industry

    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
    rowned
    -0.09
    çłĸ
    -0.08
    éĵº
    -0.08
    è¾ĩ
    -0.08
    çķĻåŃĺ
    -0.08
    èĢħçļĦ
    -0.07
    Wire
    -0.07
     Hidden
    -0.07
    chron
    -0.07
    ont
    -0.07
    POSITIVE LOGITS
    chemical
    0.13
    åĮĸå·¥
    0.12
    åĮĸåѦ
    0.11
     chemicals
    0.11
    åζèį¯
    0.11
    åĮĸåѦåĵģ
    0.11
     chemical
    0.11
    åij±
    0.10
     Chemical
    0.10
    åĮ»èį¯
    0.10
    Activations Density 0.100%

    No Known Activations