© 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. 36257
    Prev
    Next
    INDEX
    Explanations

    carn or chicago

    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
    Õ¨
    -0.08
    ESS
    -0.08
    iliar
    -0.08
    ugg
    -0.08
    .Parser
    -0.08
    oko
    -0.08
     Sung
    -0.08
    tures
    -0.08
    Constructor
    -0.08
    åĽ½åľŁ
    -0.08
    POSITIVE LOGITS
    èĤĮèĤ¤
    0.09
    é»į
    0.09
    éĢ®
    0.09
    è§ģè¯Ĩ
    0.09
     Mellon
    0.09
    ero
    0.08
    ä¸Ģé¡¿
    0.08
    èģ¿
    0.08
    ium
    0.08
    éĺİ
    0.08
    Activations Density 0.005%

    No Known Activations