© 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. 36138
    Prev
    Next
    INDEX
    Explanations

    remote communication and services

    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
    iaux
    -0.11
    ç¼ĵ
    -0.10
    ofil
    -0.09
    emm
    -0.09
    kontakte
    -0.08
    portun
    -0.08
     Orient
    -0.08
    æį
    -0.08
    اÙĦÙĬ
    -0.08
     golf
    -0.08
    POSITIVE LOGITS
     via
    0.12
    via
    0.11
    åįĥéĩĮ
    0.11
    è¿ľç¨ĭ
    0.11
    éģ¥è¿ľ
    0.11
    Via
    0.10
    è¿ľæĸ¹
    0.10
    äºij端
    0.10
    éģ
    0.09
    åħ¨ä¸ĸçķĮ
    0.09
    Activations Density 0.099%

    No Known Activations