© 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. 20767
    Prev
    Next
    INDEX
    Explanations

    membership and members

    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
    åħį
    -0.11
    .coords
    -0.09
    ALE
    -0.09
    伤害
    -0.09
    平淡
    -0.08
    éħ£
    -0.08
    èħ¥
    -0.08
    麻çĹ¹
    -0.08
    å¾Ģä¸Ĭ
    -0.08
    æİ©
    -0.08
    POSITIVE LOGITS
    ä¼ļåijĺ
    0.12
    åĬłåħ¥
    0.11
    membership
    0.11
     membership
    0.11
    ê°Ģìŀħ
    0.11
     memberships
    0.11
    æľĥåĵ¡
    0.11
    éĵ¶è¡Įåį¡
    0.11
    åĬłåħ¥äºĨ
    0.11
     Membership
    0.10
    Activations Density 0.065%

    No Known Activations