© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19559
    Prev
    Next
    INDEX
    Explanations

    coordinate or coordinates

    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
    วà¸Ķ
    -0.10
    loo
    -0.09
    rous
    -0.09
    ë¹Ĺ
    -0.09
     Victim
    -0.09
    otypes
    -0.08
    ÙĬÙĪÙĨ
    -0.08
    @student
    -0.08
    olib
    -0.08
    .variable
    -0.08
    POSITIVE LOGITS
     coordinates
    0.17
    åĿIJæłĩ
    0.15
    coordinates
    0.12
     Coordinates
    0.12
    _coordinates
    0.10
    è¿ĺè®°å¾Ĺ
    0.10
     coords
    0.10
    .coordinates
    0.10
    coords
    0.09
    .coord
    0.09
    Activations Density 0.344%

    No Known Activations