© 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. 37112
    Prev
    Next
    INDEX
    Explanations

    generating graphics from parameters

    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
     оÑĤмеÑĤиÑĤÑĮ
    -0.11
    çŀĦ
    -0.10
    åĴĢ
    -0.10
    æħĮ
    -0.10
    åħħå®ŀ
    -0.10
    .padding
    -0.10
     giá»įng
    -0.09
    åĵĢ
    -0.09
    å··
    -0.09
    贯穿
    -0.09
    POSITIVE LOGITS
    åĬ¨æĢģ
    0.09
    趣åij³
    0.09
    èĪŀ
    0.09
    ç¾İæĦŁ
    0.09
    è·³èĪŀ
    0.08
    animated
    0.08
     mesmer
    0.08
    å±ķé¦Ĩ
    0.08
    dance
    0.08
    çĶŁæĹ¥
    0.08
    Activations Density 0.267%

    No Known Activations