© 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. 10116
    Prev
    Next
    INDEX
    Explanations

    technology companies and products

    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
    èŀįåªĴä½ĵ
    -0.10
    çĪ°
    -0.10
    ç»ĺæľ¬
    -0.10
    æĬĸéŁ³
    -0.10
    Instagram
    -0.09
    èĩĤ
    -0.09
     NTN
    -0.09
    康åħ»
    -0.09
    ç½ijç»ľä¼łæĴŃ
    -0.08
    ahu
    -0.08
    POSITIVE LOGITS
    ç§ijæĬĢ
    0.10
    竹
    0.09
     technology
    0.09
     Computing
    0.08
     Ard
    0.08
     Technology
    0.08
    Paste
    0.08
    åĹħ
    0.08
     technologies
    0.08
    Technology
    0.08
    Activations Density 0.127%

    No Known Activations