© 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. 1387
    Prev
    Next
    INDEX
    Explanations

    choice or decision

    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
    umbo
    -0.10
    æľīå¤ļå°ij
    -0.10
    è¶
    -0.09
    祧
    -0.09
    ä¸Ģæĸ¹
    -0.09
     Tap
    -0.08
    ìłľëıĦ
    -0.08
    magnitude
    -0.08
     Higgins
    -0.08
    游åĩ»
    -0.08
    POSITIVE LOGITS
     choices
    0.27
     choice
    0.27
    çļĦéĢīæĭ©
    0.26
    choices
    0.23
    éĢīæĭ©
    0.22
    choice
    0.21
     choix
    0.20
     Choices
    0.20
    Choice
    0.19
    _choice
    0.19
    Activations Density 0.086%

    No Known Activations