© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50034
    Prev
    Next
    INDEX
    Explanations

    3D softwareMayaBlender

    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
    åĹĵåŃIJ
    -0.09
    éĻIJæŶ
    -0.09
    èĩªåľ¨
    -0.09
    åķ¥
    -0.09
    Configurer
    -0.09
     MMI
    -0.08
     meta
    -0.08
     Wid
    -0.08
    个æĢ§åĮĸ
    -0.08
     ['#
    -0.08
    POSITIVE LOGITS
    纹çIJĨ
    0.10
    浴室
    0.09
    çŁ³èĨı
    0.09
    ÑĥÑĪки
    0.08
    åį¯
    0.08
    .nodeType
    0.08
    igg
    0.08
    ä¸Ģ举
    0.08
    åĬªåĬĽ
    0.08
    çļ²
    0.08
    Activations Density 0.127%

    No Known Activations