© 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. 20786
    Prev
    Next
    INDEX
    Explanations

    names ending in -son

    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
    æ¶Ķ
    -0.10
    sWith
    -0.09
    æĪijä¸įæĺ¯
    -0.09
    posts
    -0.08
    making
    -0.08
    è¿Ļä¸ĢçĤ¹
    -0.08
    otp
    -0.08
    biz
    -0.08
    ì¸
    -0.08
    aller
    -0.08
    POSITIVE LOGITS
    çĶµåı°
    0.11
    æģ¶éŃĶ
    0.10
    ubber
    0.10
    ÌĢ
    0.10
    å´¤
    0.10
    qing
    0.09
    оÑĦ
    0.09
    arily
    0.09
    ÙĦع
    0.09
    hips
    0.09
    Activations Density 0.015%

    No Known Activations