© 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. 52525
    Prev
    Next
    INDEX
    Explanations

    spatial neighbors and adjacent areas

    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
    çĵľ
    -0.10
    åĩºåľº
    -0.09
    §
    -0.09
    çĤĻ
    -0.08
    .Cluster
    -0.08
    -bl
    -0.08
     Ùħرة
    -0.08
    паÑĢ
    -0.08
    åİĮ
    -0.08
    æĸ°åĨľæĿij
    -0.08
    POSITIVE LOGITS
    éļĶå£ģ
    0.11
     backyard
    0.10
    æĹłäºº
    0.09
    庸
    0.09
    éĦ°
    0.09
     Hayward
    0.09
    éĺ¿éĩĮ
    0.09
    çĴ
    0.08
    è¡Ĺ
    0.08
    udas
    0.08
    Activations Density 0.059%

    No Known Activations