© 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. 48878
    Prev
    Next
    INDEX
    Explanations

    border regions

    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
    YLE
    -0.09
    clipse
    -0.09
    å¸ĸ
    -0.09
    çĭ¬ä¸ĢæĹłäºĮ
    -0.08
    ripp
    -0.08
     Pru
    -0.08
    .Branch
    -0.08
     getInfo
    -0.08
    åĬ¿å¤´
    -0.08
    欧å¼ı
    -0.08
    POSITIVE LOGITS
    è¾¹çķĮ
    0.27
     borders
    0.22
     boundaries
    0.22
     boundary
    0.22
     border
    0.20
     гÑĢаниÑĨ
    0.20
    _boundary
    0.19
    çķĮéĻIJ
    0.19
    è¾¹å¢ĥ
    0.19
    _border
    0.18
    Activations Density 0.109%

    No Known Activations