© 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. 8314
    Prev
    Next
    INDEX
    Explanations

    mobile communications and devices

    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
    èŁĨ
    -0.10
    utz
    -0.09
    habi
    -0.08
    åIJĮåŁİ
    -0.08
    isans
    -0.08
    èľĢ
    -0.08
    วย
    -0.08
    dns
    -0.08
    Ñīа
    -0.08
    sville
    -0.08
    POSITIVE LOGITS
    ility
    0.12
    éħ¹
    0.09
    ÑĢеÑĪ
    0.09
     minded
    0.09
    rary
    0.08
    大å±Ģ
    0.08
    bing
    0.08
    -minded
    0.08
    éĵµ
    0.08
    åıijå±ķ缮æłĩ
    0.08
    Activations Density 0.082%

    No Known Activations