© 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. 36168
    Prev
    Next
    INDEX
    Explanations

    front, back, behind, thru

    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
    èĸĩ
    -0.09
    çĪ·
    -0.09
    太太
    -0.09
    éķ¿åŁİ
    -0.09
    大çĪ·
    -0.09
    ç´¯
    -0.09
    äºĨåIJ§
    -0.09
    çĮĹ
    -0.09
    纥
    -0.08
    大åĬĽæİ¨è¿Ľ
    -0.08
    POSITIVE LOGITS
    çIJħ
    0.11
    éĥ¨åī¯
    0.10
    .dispatch
    0.10
    æĢ»çļĦ
    0.09
    dge
    0.09
    èŁ¾
    0.09
    .ci
    0.09
    æĢ»ä½ĵ
    0.08
    髯
    0.08
     Haley
    0.08
    Activations Density 0.077%

    No Known Activations