© 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. 9840
    Prev
    Next
    INDEX
    Explanations

    low latency, eastern, Count, plasma, PRE

    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
    èĩªèº«
    -0.09
     Arms
    -0.08
    çĶ¨åĵģ
    -0.08
    æݨè¡Į
    -0.08
    æĢİä¹Īåģļ
    -0.08
    urn
    -0.08
     sürekli
    -0.08
     magnet
    -0.08
     sand
    -0.08
     trending
    -0.08
    POSITIVE LOGITS
     latency
    0.11
    çĽĪ
    0.10
     Burke
    0.10
    æĬľ
    0.09
    okie
    0.09
    odied
    0.09
    åºŃ
    0.09
     Fog
    0.09
    XHR
    0.09
    nection
    0.09
    Activations Density 0.058%

    No Known Activations